Filter by type:

Sort by year:

Reliability model and critical factors identification of construction safety management based on system thinking

Journal paper
Zhang, W., Zhang, X., Luo, X., Zhao, T.
Journal of Civil Engineering and Management, Vol 25, Issue 4, page 362-379

Abstract
Safety is a key objective of construction management, but construction safety management is complex due to various types of technical and management factors. If critical factors can be identified and corresponding measurements can be adopted, it will be more direct and effective to improve safety performance. In this paper, by using the system thinking method, construction safety management is considered as a system and decomposed into six subsystems and related management factors. The fuzzy fault tree analysis method was used to build a reliability analysis model and reveal the failure probabilities of factors in the safety organization management subsystem. Through a questionnaire survey conducted in Wuhan, China, the pivotal importance degrees and average occurrence probabilities of basic factors are figured out. On the basis of that, nine critical factors of the safety organization management subsystem are identified and corresponding improvement measurements are proposed. More, a case study of Hangzhou underground railway tunnel collapse accident in 2008 is conducted, which verifies that the framework of construction safety management based on system thinking can be a useful tool for identifying faults or failure reasons of construction safety management.

Keyword
construction, safety management, reliability, system thinking, fuzzy fault tree

Factors Influence China’s Off-Site Construction Technology Innovation Diffusion

Journal paper
Dou, Y., Xue, X., Zhao, Z., Luo, X.
Sustainability 2019, 11(7), 1849

Abstract
Technology innovation is a key to Off-Site Construction (OSC), but it can achieve economic and social benefits through diffusion. Previous research mainly focused on the optimization or on-site applications of OSC technology innovation; little on its diffusion-related analysis. Diffusion performance generally leads to a faster and deeper diffusion of OSC technology innovation. To study what influence the diffusion performance of OSC technology innovation, the authors first determined the research border and proposed four hypotheses, and then conducted a questionnaire in various China’s construction companies. After investigating 119 construction companies for three months, 151 valid responses were collected and analyzed using Hierarchical Regression and bootstrap-based mediation test approaches. The results found that both market and government had significant impacts on the diffusion performance with comparable influence degree (0.282** and 0.255**), the government played a dual-mediating effect with network power simultaneously (effect value is 0.215) and the technical versatility had a significant indirect influence (>0.204**) but weak direct impact (0.094) on the diffusion performance of OSC technology innovation. The conclusions explored the influence mechanism of different factors on the diffusion of OSC technology innovation and provided practical suggestions for both construction companies and government authorities to promote the development of OSC.

Keywords
diffusion performance; dual-mediating; moderated mediating; technology innovation; off-site construction

Spatial granularity analysis on electricity consumption prediction using LSTM recurrent neural network

Journal paper
Zheng, Z., Chen, H., Luo, X.
Energy Procedia, Volume 158, February 2019, Pages 2713-2718

Abstract
The building sector takes a large proportion of electricity consumption and carbon emission in high-density urban areas. To reduce the carbon emissions and use energy more efficiently in the building sector, home energy management system (HEMS) is proposed and used. In the HEMS, the prediction of electricity consumption in the short-term future is used to support the decision makings in the HEMS. Although there existed a number of studies in the prediction of electricity consumption in buildings, there lacks a spatial analysis in the prediction performance, especially on the appliance or sub-meter level and household level. The authors made an assumption that by the performance of household energy consumption prediction can be significantly improved if the prediction is aggregated from the prediction data at the appliance or sub-meter level. Next, two typical datasets are used to validate the assumption by comparing the prediction performance of aggregating the prediction data at appliance level and the one of making direct prediction at the household level. The models used for the prediction are standard stateful long short-term memory (LSTM) neural networks, which have been proofed to be promising in load prediction by previous studies. The results from the comparison validated the assumption, showing that the prediction performance can be significantly improved if prediction is made at the appliance-level first and then aggregated to get the household-level prediction. Therefore, the authors conclude that prediction at the finer appliance granularity level can significantly improve the performance of household-level electricity prediction.

Keywords
electricity consumption prediction; LSTM model; appliance level; submeter level; household level; spatial granularity analysis

Electricity load decomposition prototype for household appliances: System Design and Development

Journal paper
Lam, C., Zheng, Z., Luo, X.
Energy Procedia, Volume 158, February 2019, Pages 3158-3163

Abstract
The growing interest in green building is driving the development of energy efficiency building models. One of the essential elements is an effective and efficient Energy Management system. Traditionally, the system contains lots of meters measuring each appliance. Non-Intrusive Load Monitoring (NILM) is a technique for estimating power consumption of each appliance by disaggregating the end-use power consumption measured by a single meter. However, existing NILM are facing two main problems: 1) some of the small appliances and the similar appliances cannot have their power consumption estimated, and 2) NILM requires a long learning process, which means that a new learning process might be needed if a new appliance is connected. To tackle these problems, this paper proposes to use Intrusive Signature (IS) and Power Line Communication (PLC) for circuit-level load decomposition. The paper focuses on the development of a device using frequency domain signature as the IS. The prototype is developed and deployed on the circuit. The results show an accuracy between 83% to 93%.

Keywords
Electricity Decomposition; Intrusive Signature; Circuit Level; Power Line Communication; Small Appliance

Multisource Fusion Framework for Environment Learning–Free Indoor Localization

Journal paper
Chen, H., Luo, X., Ke, J.
Journal of Computing in Civil Engineering, Volume 32 Issue 5 - September 2018

Abstract
At the core of context-aware jobsite management is location information. For outdoor environments, global positioning systems (GPSs) are widely used. For indoor environments, however, an effective localization system has yet to be fully developed. Existing indoor localization systems usually rely on prior or real-time environment learning, and with just a slight change in the jobsite environment their performances degrade. Furthermore, localization systems that rely on a single sensor can hardly be everything a project manager would want—inexpensive, accurate, and easy to develop. Therefore, to simplify the deployment and enhance the robustness of localization for a dynamic environment, this work proposes a multisensor fusion framework. To simulate a typical residential jobsite’s indoor environment (with moving workers and ongoing activities), this work relies on two testbeds—an office area of 274m2 with dynamic traffic flow and a lab of 92m2 with ongoing lab tests. During working hours, researchers conducted performance evaluation tests in the testbeds. The results indicate that with simpler deployment the multisensor fusion algorithm was able to achieve the same accuracy level as existing systems without needing prior environment learning.

Keywords
Managers, Global positioning systems, Information management, Traffic flow, Probe instruments, Flow simulation, Project management, Traffic models

Transfer learning and deep convolutional neural networks for safety guardrail detection in 2D images

Journal paper
Kolar, Z., Chen, H., Luo, X.
Automation in Construction, Volume 89, May 2018, Pages 58-70

Abstract
Safety has been a concern for the construction industry for decades. Unsafe conditions and behaviors are considered as the major causes of construction accidents. The current safety inspection of conditions and behaviors heavily rely on human efforts which are limited onsite. To improve the safety performance of the industry, a more efficient approach to identify the unsafe conditions on site is required to supplement the current manual inspection practice. A promising way to supplement the current manual safety inspection is automated and intelligent monitoring/inspection through information and sensing technologies, including localization techniques, environment monitoring, image processing and etc. To assess the potential benefits of contemporary technologies for onsite safety inspection, the authors focused on real-time guardrail detection, as unprotected edges are the ones cause for workers falling from heights.
In this paper, the authors developed a safety guardrail detection model based on convolutional neural network (CNN). An augmented data set is generated with the addition of background image to guardrail 3D models and used as training set. Transfer learning is utilized and the Visual Geometry Group architecture with 16 layers (VGG-16) model is adopted to construct the basic features extraction for the neural network. In the CNN implementation, 4000 augmented images were used to train the proposed model, while another 2000 images collected from real construction jobsites and 2000 images from Google were used to validate the proposed model. The proposed CNN-based guardrail detection model obtained a high accuracy of 96.5%. In addition, this study indicates that the synthetic images generated by augment technology can be used to create a large training dataset, and CNN-based image detection algorithm is a promising approach in construction jobsite safety monitoring.

Keywords
Computer vision; Construction safety; Guardrail detection; Convolutional neural networks; Transfer learning; VGG-16

Decision framework for optimal installation of outriggers in tall buildings

Journal paper
Zhou, K., Li, QS., Luo, X.
Automation in Construction, Volume 93, September 2018, Pages 200-213

Abstract
Installation sequence of outrigger system, an important structural component of high-rise buildings, is often determined simply based on engineers’ experience, posing a threat to the structural safety and stability. This paper proposes a comprehensive decision framework for developing the optimal installation plan for the outrigger system, in which construction simulation and safety analysis of the overall structural system are well integrated. The proposed framework is applied to a super-tall building with a height of 600 m. First, the finite element method (FEM) model of the skyscraper used for construction simulation is validated by field measurements during Typhoon ‘Nida’. Based on the validated FEM model, the lower limits (earliest) for installing the outrigger system are obtained through the outrigger trusses’ safety analysis for the service stage of the building, while the upper limits (latest) are determined through the analysis of structural stiffness and global stability for the construction stage. Thereupon, a rational plan is established for installing the outrigger system into the skyscraper, and the viability and efficiency of the proposed decision framework are examined by analyzing the construction simulation models. The outcomes of this study are expected to be of use and interest for structural engineers and researchers involved in construction management of installing outriggers into high-rise buildings, and therefore provide valuable implications for other similar projects.

Keywords
Super-tall building; Decision framework; Optimal installation sequence of outrigger; Construction simulation; Structural safety and stability

Major knowledge diffusion paths of mega-project management: A citation-based analysis

Journal paper
Wu, H., Xue, X., Zhao, Z., Wang, Z., Shen, Q.P., Luo, X.
Project Management Journal 2018

Abstract
This article integrates social network analysis and main path analysis to investigate progress in megaproject management (MPM) from the perspective of knowledge diffusion. After measuring three major knowledge diffusion paths of MPM, the authors find that MPM is mainly driven by a set of problems and puzzles. The findings provide an exciting opportunity to advance existing understanding of MPM from an alternative angle of knowledge diffusion that considers the underlying associations among publications. Moreover, this article employs quantitative methods to examine citation data of publications, thus providing more unbiased and in-depth analysis to illustrate the development of MPM.

Keywords
knowledge diffusion, main path analysis, mega-project management, modularity optimization

Study on Flow Field Characteristics of the 90° Rectangular Elbow in the Exhaust Hood of a Uniform Push–Pull Ventilation Device

Journal paper
Wu, X., Liu, L., Luo, X., Chen, J., Dai, J.
Int. J. Environ. Res. Public Health 2018, 15(12), 2884

Abstract
A uniform push–pull ventilation device can effectively improve indoor air quality (IAQ). The 90° rectangular elbow is an important part of the push–pull ventilation device. This paper analyzes the flow field characteristics of the 90° rectangular elbows under different working conditions. This was done by using computational fluid dynamics (CFD) simulation (Fluent). The flow lines, velocity and pressure distribution patterns of the elbow flow field are revealed in detail. The wind velocity non-uniformity and wind pressure non-uniformity of the 90° rectangular elbows with different coefficients of radius curvature R and rectangular section height h are also compared. The results show that when R ≥ 2.5 h, the wind flow traces inside the elbow are basically parallel lines. At the same time, the average wind velocity and the average wind pressure are stable. Also, the wind velocity non-uniformity and wind pressure non-uniformity decrease with the increase of R. Therefore, considering the space and material loss caused by an increase in radius of curvature, the elbow with R = 2.5 h can be used as the best design structure for the 90° rectangular elbow, which is of great significance for improving the control effect of dust and toxic pollutants in a uniform push–pull ventilation device.

Keywords
uniform push–pull ventilation device; 90° rectangular elbow; radius of curvature; non-uniformity; flow field characteristics

Development of Construction Workers Job Stress Scale to Study and the Relationship between Job Stress and Safety Behavior: An Empirical Study in Beijing

Journal paper
Wu, X., Li, Y., Yao, Y., Luo, X., He, X., Yin, W.
Int. J. Environ. Res. Public Health 2018, 15(11), 2409

Abstract
Job stress is considered one of the critical causes of construction workers’ unsafe behaviors. As a mainstay industry in many countries, the construction industry has a considerable number of employees and the research on how job stress affects workers’ unsafe behaviors has important theoretical and practical significance to improve construction safety performance through better job stress management. In this study, the authors thoroughly reviewed the literature and conducted semi-structured interviews to identify the dimensions of job stress, designed the job stress scale and cited the safety behavior measurement scale. After that, a questionnaire survey was developed using the proposed measurement scale and distributed to the construction employees from a project in Beijing. One hundred fifty responses were collected and analyzed using reliability analysis to validate the scale’s internal consistency. Results from factor analysis indicate that the scales of job stress measurement can be grouped into six dimensions. To demonstrate the applicability of the developed scale on construction safety management research, the collected data was used to test the hypothesis that job stress has a negative correlation with safety behavior. Results show that the hypothesis is valid, and there is a negative correlation between job stress and safety behavior. In addition, finer results of the relationship between the six dimensions of job stress and safety behavior can be obtained. In summary, this study developed an improved stress scale for construction workers in China, and the proposed scale was validated by analyzing the data from an empirical study in Beijing.

Keywords
construction worker; job stress scale; safety behavior; reliability analysis

A Supervised Event-Based Non-Intrusive Load Monitoring for Non-Linear Appliances

Journal paper
Zheng, Z., Chen, H., Luo, X.
Sustainability 2018, 10(4), 1001

Abstract
Smart meters generate a massive volume of energy consumption data which can be analyzed to recover some interesting and beneficial information. Non-intrusive load monitoring (NILM) is one important application fostered by the mass deployment of smart meters. This paper presents a supervised event-based NILM approach for non-linear appliance activities identification. Firstly, the additive properties (stating that, when a certain amount of specific appliances’ feature is added to their belonging network, an equal amount of change in the network’s feature can be observed) of three features (harmonic feature, voltage–current trajectory feature, and active–reactive–distortion (PQD) power curve features) were investigated through experiments. The results verify the good additive property for the harmonic features and Voltage–Current (U-I) trajectory features. In contrast, PQD power curve features have a poor additive property. Secondly, based on the verified additive property of harmonic current features and the representation of waveforms, a harmonic current features based approach is proposed for NILM, which includes two main processes: event detection and event classification. For event detection, a novel model is proposed based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Compared to other event detectors, the proposed event detector not only can detect both event timestamp and two adjacent steady states but also shows high detection accuracy over public dataset with F1-score up to 98.99%. Multi-layer perceptron (MLP) classifiers are then built for multi-class event classification using the harmonic current features and are trained using the data collected from the laboratory and the public dataset. The results show that the MLP classifiers have a good performance in classifying non-linear loads. Finally, the proposed harmonic current features based approach is tested in the laboratory through experiments, in which multiple on–off events of multiple appliances occur. The research indicates that clustering-based event detection algorithms are promising for future works in event-based NILM. Harmonic current features have perfect additive property, and MLP classifier using harmonic current features can accurately identify typical non-linear and resistive loads, which could be integrated with other approaches in the future.

Keywords
event-based NILM; additive property; harmonic currents; DBSCAN clustering based events detector; MLP classifier; non-linear appliances

Safety challenges and improvement strategies of ethnic minority construction workers: a case study in Hong Kong

Journal paper
Wu, C., Luo, X., Wang, T., Wang, Y., Sapkota, B.
International journal of occupational safety and ergonomics, 2019, pp 1-38.

Abstract
Due to cultural differences, ethnic minority construction workers are more difficult to manage and more vulnerable to accidents. This study aims to identify the major barriers faced by ethnic minority workers from their own perspectives and to determine potential strategies to enhance the safety climate of construction projects, thus ultimately improving their safety performance. A survey with the modified nordic safety climate questionnaire was conducted for a certain subcontractor in Hong Kong. In-depth interviews, status quo description, major challenge investigation and safety knowledge tests were also carried out. The top three most important safety challenges identified were improper stereotypes from the whole industry, lack of opportunities for job assignment and language barriers. To improve the safety performance, employers should allocate sufficient personal protective equipment and governments should organize unannounced site visits more frequently. Also, the higher-level management should avoid giving contradictory instructions to foremen against the standards of supervisors.

Keywords
ethnic minority workers, construction safety, safety climate, safety challenges, safety improvement strategies

Multi-Index Evaluation for Flood Disaster from Sustainable Perspective: A Case Study of Xinjiang in China

Journal paper
Dou, Y., Xue, X., Zhao, Z., Luo, X., Ji, A., Luo, T.
Int. J. Environ. Res. Public Health 2018, 15(9), 1983

Abstract
The floods have undermined the sustainable construction of cities because of their sudden and destruction. To reduce the losses caused by floods, it is necessary to make a reasonable evaluation for historical floods and provide scientific guidance for future precaution. Previous research mainly used subjective/objective weights or barely made static analysis without considering the uncertainty and ambiguity of floods. Therefore, this study proposed a variable fuzzy recognition model, based on combined weights, to evaluate floods, including the determination of index weights and the choice of evaluation model. To make the index weights reflect both subjective experience and objective data, the combined weights were proposed and calculated based on the principle of minimum identification information. Then, the relative membership degree matrix and evaluation results can be worked out by the variable fuzzy recognition model. Conclusions indicated that the combined weights were more convincing than simply subjective or objective weights. Moreover, the variable fuzzy recognition model, by changing model parameters, got stable evaluation results of the sample data. Therefore, the model can improve the credibility of evaluation and the conclusions can provide reasonable suggestions for management departments.

Keywords
multi-index evaluation; combined weights; variable fuzzy recognition model; sustainable perspective

Exploring the Emerging Evolution Trends of Urban Resilience Research by Scientometric Analysis

Journal paper
Wang, L., Xue, X., Zhang, Y., Luo, X.
Int. J. Environ. Res. Public Health 2018, 15(10), 2181

Abstract
Numerous studies in urban resilience have been published in the past decade. However, only a few publications have tracked the evolution trends of urban resilience research, the findings of which can serve as a useful guide for scholars to foresee worth-effort research areas and make the best use of precious time and resources. In order to fill the research gap, this study performed a scientometric analysis on the evolution trends of urban resilience research using a versatile software package-CiteSpace. The scientomentric analysis focuses on distribution of lead authors and their institutions, high frequency categories and keywords, high influential journals, author contribution, and evolutionary trends based on co-author analysis, co-word analysis, co-citation analysis and cluster analysis of documents. This study discoveries that first, the U.S., England, Australia, Canada, China and Sweden are the countries that make the most significant contributions in the advancement of urban resilience research; second, the existing urban resilience research focuses primarily on environmental studies, geography and planning development; third, hot topics of the urban resilience research keep shifting from 1993 to 2016; fourth, the knowledge body of urban resilience research consists of five clusters: resilience exploratory analysis, disaster resilience, urban resilience, urban resilience practice, and social-ecological systems; last, the emerging trends in urban resilience research include defining urban resilience, adaptation model, case studies, analytical methods and urban social-ecological systems, resulting in cutting-edge research areas in urban resilience.

Keywords
urban resilience; CiteSpace; Web of Science (WOS); evolution trends; scientometrics; visualization

Location-based measurement and visualization for interdependence network on construction sites

Journal paper
Yang, X., Luo, X., Li, H., Luo, X., Guo, H.
Advanced Engineering Informatics, Volume 34, October 2017, Pages 36-45

Abstract
Appropriately assigning workers to tasks is vitally important in project management. To do this, project managers need to objectively and effectively measure and visualize the spatiotemporal orders of real construction process as well as coordination structure of the workforce. However, currently there is no method/tool available to project managers to represent spatiotemporal orders of construction processes. To address this issue, this paper presents a novel approach to measuring the real spatiotemporal order of onsite tasks as well as the task interdependence by an interdependence network. This approach extracts the distance of workspace distributions as a key interdependence indicator from historical location tracks across different construction stages according to the area-restricted nature of construction activities. It then integrates generated interdependence into a network over time, to imply the cooperation patterns in stages and a task delivery across stages with a holistic view. To validate the approach, location data were collected from 31 workers working in a high-rise housing construction project for one week to construct the interdependence network of this project, which was used to quantitatively evaluate the performance of construction schedule, assignments and cooperation. Results show that the interdependence network is able to provide insightful information on how workers perform individual tasks onsite and it is also an effective tool to identify and display the interactions among site workers.

Keywords
Construction activities; Interdependence network; Quantitative measurement; Location-based service

The Spillover Effects on Employees’ Life of Construction Enterprises’ Safety Climate

Journal paper
Wu, X., Yin, W., Wu, C., Luo, X.
Sustainability 2017, 9(11), 2060

Abstract
Organizational safety climate will produce spillover effects and thus affect the individuals’ performance in their family life. As a mainstay industry in many countries, the construction industry has a considerable number of employees and the research on the spillover effects from the safety climate of construction enterprises has important theoretical and practical significance to improve the safety behavior of construction employees in their family life. In this study, we thoroughly reviewed the literature to identify the dimensions of the safety climate spillover, obtain empirical data of the construction employees through a questionnaire survey, and use the data analysis method to study the spillover effects of the safety climate of the construction enterprises from the perspective of work–family integration, and reveal its influence mechanism. This study developed a questionnaire to measure the safety climate spillover of the construction enterprises including two dimensions, namely values and behaviors, with nine measured items. Management commitment and safety attitude in the safety climate were positively related to the spillover, and management commitment had the greatest impact on the spillover, while the other components were not significantly related to the spillover. The two forms of spillover, values and behaviors, were mutually influential, and the safety climate had a more significant impact on the values. This paper contributes to the current safety research by developing a factor structure of spillover effects of the safety climate on the lives of construction employees, thus providing a more profound interpretation of this crucial construct in the safety research domain. The spillover effects of the safety climate’s measurement questionnaire serve as an important tool for spillover among construction enterprises. Findings can facilitate improvement in both theories and practices related to the spillover effects of the safety climate on the lives of employees. This paper studies the spillover effects of construction enterprises’ safety climate, to reveal its influencing mechanism, and can thus provide theoretical guidance for preventing safety accidents in employees’ life.

Keywords
safety climate; spillover; construction enterprises; values; behaviors

HVAC Energy Saving in IPS-enabled Large Space: An Occupancy Distribution Based Demand-driven Control Approach

Journal paper
Wang, W., Lu, Y., Huang, G., Luo, X., Chen, J.
Energy Procedia, Volume 105, May 2017, Pages 2083-2088

Abstract
Occupancy attracts an increasing attention in recent building energy efficiency research through enabling more sophisticated control strategies. With the development of latest indoor positing systems (IPS), the facility managers are able to detect the geospatial distribution of building occupants. Based on such information, this paper proposes a demand-driven control system for HVAC control in large spaces to reconcile occupants’ thermal comfort demand and energy consumption. Comparing to conventional temperature and CO2 based HVAC control systems, the new approach integrates the indoor positions of occupants and a demand-oriented and PID-based ventilation control mechanism. An computational fluid dynamic simulation is constructed to valid the proposed control system. Air supply flow rate and temperature distribution are captured for three sample cases that have even and uneven occupancy distributions in the simulation. By avoiding overcooling and unnecessary cooling, the proposed approach could save a significant amount of electrical consumption from HVAC operation.

Keywords
occupancy distribution; build energy efficiency; temperature distribution; indoor positioning system

Severity Prediction Models of Falling Risk for Workers at Height

Journal paper
Chen, H., Luo, X.
Procedia Engineering, Volume 164, 2016, Pages 439-445

Abstract
Construction industry has one of the highest accident and fatality rates among other major industries, with more than 60,000 fatal accidents each year worldwide. Falling from height is one of the leading causes of fatalities and injuries in construction. Passive protection devices (e.g., safety net) have been used to minimize the impact of falling from height for ages, while proactive warning systems appear recently to alert the workers when they are at risks of falling. To provide appropriate warnings to the worker but not to distract them due to the false alarm, the falling risk needs to be carefully evaluated. In this paper, the authors introduced algorithms for falling risk prediction and evaluated their performance. Injuries records during 2005 to 2015 were extracted from the OSHA database and 1161 intact falling-related record were used in this study. K-Modes, RBF network and Decision Trees are chosen to build three risk prediction models, and the performance of those three proposed models were evaluated using the OSHA injuries record data. The results indicate that the DT-based falling risk prediction model has the best performance of 75% and the top three critical factors of falling event’s severity are distance from the ground, worker’s occupation and the source of the falling. The delivered severity prediction model provides the foundation of more accurate real time risk evaluation for workers at height.

Keywords
Falling from height; machine learning; serverity of injury; risk prediction

Utilizing BIM and Carbon Estimating Methods for Meaningful Data Representation

Journal paper
Mousa, M., Luo, X., McCabe, B.
Procedia Engineering, Volume 145, 2016, Pages 1242-1249

Abstract
The building sector releases 36% of global CO2 emissions, with 66% of emissions occurring during the operation stage of the life cycle of a building. While current research focuses on using Building Information Modelling (BIM) for energy management of a building, there is little research on the visualizing building carbon emission data in BIM to support decision makings during operation phase. This paper proposes an approach for gathering, analyzing and visualizing building carbon emissions data by integrating BIM and carbon estimation models, to assist the building operation management teams in discovering carbon emissions problems and reducing total carbon emission. Data requirements, carbon emission estimation algorithms, integration mechanism with BIM are investigated in this paper. A case is used to demonstrate the proposed approach. The approach described in this paper provides the inhabitants important graphical representation of data to determine a buildings sustainability performance, and can allow policy makers and building managers to make informed decisions and respond quickly to emergency situations.

Keywords
BIM; AEC; Carbon Emissions; Buildings; Life Cycle Carbon; Residential; Energy Management

The finite element discretized symplectic method for composite mode III cracks

Journal paper
C.Xu, Z. Zhou, A.Y.T. Leung, X. Xu, X. Luo
Engineering Fracture Mechanics, Volume 140, May 2015, Pages 43-60

Abstract
A finite element discretized symplectic method is proposed to compute the stress intensity factors (SIFs) of interface cracks in multi-material composites subjected to anti-plane loading. The whole body is divided into a near field containing a crack to be solved analytically and a far field to be solved by conventional finite elements. In the near field, analytical series solutions are found by the Hamiltonian formulation. The unknown displacements of the densely populated finite elements are transformed to a handful of unknown coefficients of the series. After combining with the far field, the SIFs are actually the first few coefficients.

Keywords
Finite element discretized symplectic method; Stress intensity factor; Anti-plane; Composites; Interface crack

Location-Aware Sensor Data Error Impact on Autonomous Crane Safety Monitoring

Journal paper
Luo,X., Leite, F., O’Brien, W.J.
Journal of Computing in Civil Engineering, Volume 29 Issue 4 - July 2015

Abstract
Emerging sensing technologies offer a solution to improve jobsite safety performance by providing location information to determine a worker’s safety situation regarding proximity to dangers. However, due to the imperfections inherent in real-world sensor data, the collected location data might be imperfect (missing, uncertain, erroneous, and inconsistent). Among those types of imperfection, error is one of the most common. In many cases, jobsite safety monitoring applications are built on the assumption that the collected location data represent the exact situation, which might not be true due to erroneous data. However, data errors and their potential impacts on the decisions in autonomous jobsite safety monitoring systems have not been substantially studied. This paper describes an autonomous jobsite safety monitoring testbed developed to collect data from location-aware sensors. The authors developed six jobsite crane-safety monitoring test scenarios to replicate the construction activities on a full-scale jobsite and used the collected data, as well as simulated sensor data at various error levels, to quantify the impacts on decision-making performance in terms of precision and recall of workers’ dangerous situations. The results indicated that the worst performance appears near the transition area of different risk levels (red to yellow/yellow to green) and the performance degrades significantly after the standard deviation of the localization errors reaches 2 cm in the testbed, corresponding to 2 m in a jobsite. The study provides researchers with an understanding of how much data errors impact safety monitoring system performance and guide future research directions.

Keywords
Safety, Labor, Data collection, Cranes, Occupational safety, Probe instruments, Full-scale tests, Errors (statistics)

Exploring Approaches to Improve the Performance of Autonomous Monitoring with Imperfect Data in Location-aware Wireless Sensor Networks

Journal paper
Luo,X., O’Brien, W.J., Leite, F., Goulet, J.
Advanced Engineering Informatics, Volume 28, Issue 4, October 2014, Pages 287-296

Abstract
In recent years, information and sensing technologies have been applied to the construction industry to collect and provide rich information to facilitate decision making processes. One of the applications is using location data to support autonomous crane safety monitoring (e.g., collision avoidance and dangerous areas control). Several location-aware wireless technologies such as GPS (Global Positioning System), RFID (Radio-frequency identification), and Ultra-Wide Band sensors, have been proposed to provide location information for autonomous safety monitoring. However, previous studies indicated that imperfections (errors, uncertainty, and inconsistency) exist in the data collected from those sensors and the data imperfections have great impacts on autonomous safety monitoring system performance. This paper explores five computationally light-weight approaches to deal with the data imperfections, aiming to improve the system performance. The authors built a scaled autonomous crane safety monitoring testbed with a mounted localization system to collect location data and developed five representative test cases based on a live construction jobsite. Seven hundred and sixty location readings were collected at thirty-eight test points from the sensors. Those location data was fed into the reasoning mechanisms with five approaches to generate the safety decisions at those thirty-eight test points and evaluate system performance in terms of precision, recall and accuracy. The results indicate that system performance can be improved if at least ten position readings from sensors can be collected at small intervals at any location along the moving path. However, by including additional data such as velocity and acceleration that may be read from devices mounted on workers, localization error may be significantly reduced. These findings represent a path forward to improve localization accuracy by mixing imperfect data from the sensed environment with supplemental input.

Keywords
Wireless sensors; Safety monitoringl; Data error; Missing data; Tower crane; Bayesian network

Mixed-mode thermal stress intensity factors from the finite element discretized symplectic method

Journal paper
Zhou, Z., Leung, A.Y.T., Xiao, X., Luo, X.
International Journal of Solids and Structures, Volume 51, Issues 21–22, 15 October 2014, Pages 3798-3806

Abstract
A finite element discretized symplectic method is introduced to find the thermal stress intensity factors (TSIFs) under steady-state thermal loading by symplectic expansion. The cracked body is modeled by the conventional finite elements and divided into two regions: near and far fields. In the near field, Hamiltonian systems are established for the heat conduction and thermoelasticity problems respectively. Closed form temperature and displacement functions are expressed by symplectic eigen-solutions in polar coordinates. Combined with the analytic symplectic series and the classical finite elements for arbitrary boundary conditions, the main unknowns are no longer the nodal temperature and displacements but are the coefficients of the symplectic series after matrix transformation. The TSIFs, temperatures, displacements and stresses at the singular region are obtained simultaneously without any post-processing. A number of numerical examples as well as convergence studies are given and are found to be in good agreement with the existing solutions.

Keywords
Finite element discretized symplectic method; Thermal stress intensity factor; Symplectic method; Analytical solutions

Comparative Evaluation of Received Signal Strength Index (RSSI)-based Indoor Localization Techniques for Construction Jobsites

Journal paper
Luo, X., O’Brien, W.J., Julien, C.
Advanced Engineering Informatics, Volume 25, Issue 2, April 2011, Pages 355-363

Abstract
This paper evaluates the accuracy of several RSSI-based localization techniques on a live jobsite and compares them to results obtained in an operating building. RSSI-based localization algorithms were tested due to their relative low cost and potential for accuracy. Four different localization algorithms (MinMax, Maximum Likelihood, Ring Overlapping Circle RSSI and k-Nearest Neighbor) were evaluated at both locations. The results indicate that the tested localization algorithms performed less well on the construction jobsite than they did in the operating building. The simple MinMax algorithm has better performance than other algorithms, with average errors as low as 1.2 m with a beacon density of 0.186/m2. The Ring Overlapping Circle RSSI algorithm was also shown to have good results and avoids implementation difficulties of other algorithms. k-Nearest Neighbor algorithms, previously explored by other construction researchers, have good accuracy in some test cases but may be particularly sensitive to beacon positioning.

Keywords
Localization; Civil construction/buildings; Radio frequency; RSSI; Model based methods

Study on the Information Flow for Construction Project Safety Management

Conference paper
Hung, S., Ke, J., Luo, X.
23rd International Conference on Advancement of Construction Management and Real Estate (CRIOCM 2018), 24/08/2018-27/08/2018, Guiyang, China

Abstract

The construction industry has been identified with the characteristics of complexity and fragment, involving several stakeholders. Projects carried out within this sector required effective collaboration and communication among multiple participants. However, the ineffective communication in construction job sites has resulted in poor safety performance, cost overrun, delays and rework due to the hazardous nature of the construction industry, which leads to the industry to lose approximately $60 billion per year globally. Construction safety management is one of the biggest challenges in this industry due to the lack of effective communication, which contributed to high accidents, injuries, and even death. Previous studies have attempted to focus on improving communication on job sites through information technologies. Despite the increasing use of IT in improving communication, safety remains a significant concern in the construction industry. The critical problem of ineffective communication on construction job sites is that there is a lack of information interoperability within the industry blocks the seamless and timely exchange of relevant information on projects. In this research, it aims to develop a safety information flow model for improving the key problem of information flow in construction safety management. The model is developed based on the document analysis and questionnaire. The model is presented in 2 modules; Module 1 presents the information required in safety management and how the information is processed in categories. Module 2 presents the right and responsibility of handling each safety information. 1404 Information Flow Paths have been identified, and the model has helped analyze the common data required in different safety management functions, which can help to enhance the integration of safety information to serve the research objectives.

Electricity load decomposition for small appliances: Prototype Development and Testing

Conference paper
Lam, C., Zheng, Z., Luo, X
10th International Conference on Applied Energy (ICAE2018), 22-25 August 2018, Hong Kong, China

Abstract

The growing interest in green building is driving the development of energy efficiency building models. One of the essential elements is an effective and efficient Energy Management system. Traditionally, the system contains lots of meters measuring each appliance. Non-Intrusive Load Monitoring (NILM) is a technique for estimating power consumption of each appliance by disaggregating the end-use power consumption measured by a single meter. However, existing NILM are facing two main problems: 1) some of the small appliances and the similar appliances cannot have their power consumption estimated, and 2) NILM requires a long learning process, which means that a new learning process might be needed if a new appliance is connected. To tackle these problems, this paper proposes to use Intrusive Signature (IS) and Power Line Communication (PLC) for circuit-level load decomposition. The paper focuses on the development of a device using frequency domain signature as the IS. The prototype is developed and deployed on the circuit. The results show an accuracy between 83% to 93%.

Spatial granularity analysis on electricity consumption prediction using LSTM recurrent neural network

Conference paper
Zheng, Z., Chen, H., Luo, X.
10th International Conference on Applied Energy (ICAE2018), 22-25 August 2018, Hong Kong, China

Abstract

The building sector takes a large proportion of electricity consumption and carbon emission in high-density urban areas. To reduce the carbon emissions and use energy more efficiently in the building sector, home energy management system (HEMS) is proposed and used. In the HEMS, the prediction of electricity consumption in the short-term future is used to support the decision makings in the HEMS. Although there existed a number of studies in the prediction of electricity consumption in buildings, there lacks a spatial analysis in the prediction performance, especially on the appliance or sub-meter level and household level. The authors made an assumption that by the performance of household energy consumption prediction can be significantly improved if the prediction is aggregated from the prediction data at the appliance or sub-meter level. Next, two typical datasets are used to validate the assumption by comparing the prediction performance of aggregating the prediction data at appliance level and the one of making direct prediction at the household level. The models used for the prediction are standard stateful long short-term memory (LSTM) neural networks, which have been proofed to be promising in load prediction by previous studies. The results from the comparison validated the assumption, showing that the prediction performance can be significantly improved if prediction is made at the appliance-level first and then aggregated to get the household-level prediction. Therefore, the authors conclude that prediction at the finer appliance granularity level can significantly improve the performance of household-level electricity prediction.

Development and Evaluation of an Augmented Reality Learning Tool for Construction Engineering Education

Conference paper
Luo, X., Cabico, C.
Construction Research Congress (CRC) 2018, 2/4/2018-4/4/2018, New Orleans, LA, USA
Abstract

Augmented reality (AR) is becoming widely used in construction industry for training, education, onsite inspection and etc. In this paper, the authors developed a AR-based learning tool for construction engineering students and evaluated the impact of AR for students’ learning performance. The tool, ARBridge, was developed using PTC Vuforia, AutoDesk Revit, Sketchup, and Unity. Various types of bridge structure can be supported for learning in this tool. After completion of the tool development, 40 undergraduate students are divided into experimental group and control group to learn a mini-module on bridge engineering using the ARBridge and traditional education way. Pre-experiment and post-experiment tests were conducted for the 40 students. Result findings collected and analyzed from case-based experiment, feedback survey and interview demonstrated the suitability of the app to evidently enhance students’ learning experience and knowledge-acquisition process through application of the technology in educational settings as a supplementary teaching material in learning components of complex bridge structures.

Keywords

Materials processing, Construction materials, Construction equipment, Bridge components, Inspection, Training, Engineering education, Students

Improving RSSI-based Indoor Localization Performance by Integrating BIM

Conference paper
Chen, H., Luo, X., Guo, J.
2017 International Workshop on Computing in Civil Engineering (IWCCE 2017), 25/06/2017 - 27/06/2017, Seattle, United States of America
Abstract

Localization for the resources and workers on construction sites is significant and essential for effective construction projects management. Since global positioning system (GPS) usually does not work indoor, indoor localization is critical for jobsite indoor resource and labor management. However, due to the complex and variable environment situation on construction jobsites, accuracy and quick deployment remains to be two primary challenges for practical and wide adoption of localization technology on jobsites. As radio signal strength index (RSSI) based indoor localization techniques have relatively low costs and easy deployments comparing to other techniques (e.g., Ultra Wide Band, Ultrasonic), RSSI-based localization technologies have attracted much attention in construction industry. However, the accuracy of existing RSSI-based technologies is still not satisfactory. Therefore, the authors proposed to improve the accuracy of RSSI-based indoor localization technology by utilizing the information extracted from BIM in the localization algorithm. A lab with BIM model is used as the testbed for the algorithm’s validation at 19 discrete locations and one continuous moving path. The test results indicate that the localization accuracy can be improved by filtering up to 25.6% of the infeasible positions based on building information modelling (BIM).

Keywords

Resource management, Labor, Global positioning systems, Algorithms, Building information modeling, Construction sites, Construction costs, Model accuracy

A Multi-player Virtual Reality-based Education Platform for Construction Safety

Conference paper
Luo, X., Wong, C.K., Chen, J.
16th International Conference on Computing in Civil and Building Engineering (ICCCBE2016). Osaka, Japan. July 6 – 8, 2016

Abstract

Construction is one of the industries with the highest fatality and injuries rate around the world. Studies indicated that human error is one of the key contributors of construction accidents. Although human error is inevitable, construction workers can acquire a range of skills and knowledge to improve the ability to identify and assess risk through training and experience. However, researchers have raised questions about the effectiveness of the existing construction safety training since the industry still remains among the most dangerous to work in. Recent advancement in virtual reality (VR) has offered us with the opportunities for providing a more effective approach for safety training. However, the existing research and applications on VR mainly focused on single user applications with static environments, which cannot fully address the challenges posed by the dynamic and teamwork characteristics of construction projects. In this paper, the authors presented a framework supporting the safety knowledge integration, building information utilization, and multi-user interaction. In the framework, a trainee’s performance can be monitored in real-time and stored in the database to support the training performance analysis. A prototype multi-player VR-based education platform is developed following the proposed framework using Oculus Rift, Unity 5, C# and BIM application. The education platform presented in this paper provides an effective approach for safety training in an immersive environment to simulate the interactions among workers/equipment as well as provides informative and timely feedback for trainee.

Keywords

Virtual Reality, Construction Safety Training, Falling Objectives, Interactive Playing

Probability Prediction Algorithms of Falling Risk for Workers at Height

Conference paper
Chen, H., Luo, X.
Creative Construction Conference 2016, 25 Jun 2016 - 29 Jun 2016, Budapest, Hungary

Abstract

Construction industry has one of the highest accident and fatality rates among other major industries, with more than 60,000 fatal accidents each year worldwide. Falling from height is one of the leading causes of fatalities and injuries in construction. Passive protection devices (e.g., safety net) have been used to minimize the impact of falling from height for ages, while proactive warning systems appear recently to alert the workers when they are at risks of falling. To provide appropriate warnings to the worker but not to distract them due to the false alarm, the falling risk needs to be carefully evaluated. In this paper, the authors introduced algorithms for falling risk prediction and evaluated their performance. Injuries records during 2005 to 2015 were extracted from the OSHA database and 1161 intact falling-related record were used in this study. K-Modes, RBF network and Decision Trees are chosen to build three risk prediction models, and the performance of those three proposed models were evaluated using the OSHA injuries record data. The results indicate that the DT-based falling risk prediction model has the best performance of 75% and the top three critical factors of falling event’s severity are distance from the ground, worker’s occupation and the source of the falling. The delivered severity prediction model provides the foundation of more accurate real time risk evaluation for workers at height.

Keywords

Falling from height; machine learning; severity of injury; risk prediction

Revealing the “Invisible Gorilla” in Construction: Assessing Mental Workload through Time-frequency Analysis

Conference paper
Chen, J.,Ren, B.,Song, X., Luo, X.
The International Symposium on Automation and Robotics in Construction and Mining, RIL; IAARC; University of OULU, OULU, Finland, 15-18 June 2015
AbstractConstruction companies suffer huge losses due to labor fatalities and injuries. Since more than 70% of all accidents are related to human activities, detecting and mitigating human-related risks holds the key to improve the safety condition of construction industry. Many research reveals the psychological and emotional conditions of workers could contribute to the fatalities and injuries. More recent observations in the area of neural science and psychology suggest inattentional blindness is one major cause of unexpected human related accidents. Due to the limitation of human mental workload, labors are vulnerable to unexpected hazards while they are focusing on complicated construction tasks. Therefore, detecting the mental conditions of workers could indicate the hazards level of unexpected injuries. However, there is no available measurement can monitor construction workers’ mental condition and related hazards. This proposed research aims at proposing a measurement framework to evaluate such hazards through a neural time-frequency analysis approach. At the same time, the researchers also developed a prototype wearable Electroencephalography (EEG) safety helmet to enable the neural information collection.

Keywords
Construction Safety; Mental Workload; Electroencephalography (EEG)

A hybrid control mechanism for stabilizing a crane load under environmental wind on a construction site

Conference paper
Ren, B., Leung, A.Y.T., Chen, J., Luo, X.
2015 ASCE International Workshop on Computing in Civil Engineering. IWCCE 2015; University of Texas at Austin. Austin; United States; 21 June 2015 through 23 June 2015
Abstract

Tower cranes are widely used in construction jobsite for their efficiency. However, tower cranes and construction workers themselves suffer a significant safety hazards from natural sway of payloads. Besides, the external disturbance of wind leads to additional sway and intensifies the oscillation amplitude of crane load on construction site. Therefore, we propose a hybrid control mechanism that combine electronic and mechanical gyroscopes to produce a balancing torque, keeping crane load stable. We assume the crane load as in the case of the inverted pendulum and simulate the oscillation movement under continuous wind. A hybrid control mechanism is designed and developed, with the electronic gyroscope to track the real-time position and orientation of payload, with the mechanical gyroscope as an actuator of collected feedback to control the oscillation amplitudes. A wind tunnel test has been conducted to validate the developed hybrid mechanism.

Keywords

Hybrid methods, Cranes, Occupational safety, Wind loads, Environmental issues, Construction sites, Oscillations, Load factors

Evaluating the Impact of Location-aware Sensor Data Imperfections on Autonomous Jobsite Safety Monitoring

Conference paper
Luo, X., O’Brien, W.J., Leite, F.
2013 ASCE International Workshop on Computing in Civil Engineering. Los Angeles, California, USA. 8 pages

Abstract
Construction is one of the industries with the highest fatality, non-fatal injuries and illness rates across the United States (CPWR, 2008). Although construction professionals have made great efforts to improve safety training, site supervision and design for safety (among others), the safety performance in construction is still not satisfactory due to human errors and lack of situational awareness during construction activities. Recent advances in sensing and computing technologies offer a solution for improving safety performance by providing rich information about location and, hence, worker safety. Our research envisions an autonomous jobsite safety monitoring system which utilizes distributed data and information collected from various sources (RFID, localization sensors, accelerometers, load cell sensors and building information models). The research is divided into three phases: (1) knowledge elicitation; (2) development and deployment of the autonomous safety monitoring system in a distributed computing environment; and (3) exploring the impacts of data imperfections situations (e.g., erroneous or missing data) on the safety monitoring system and approaches to reduce the impacts of the imperfections on the safety system. Prior research has reported on the first two phases (Julien, et al, 2005; Luo, et al, 2011; O’Brien, et al, 2008). This paper reports the preliminary results of evaluating the impacts of data imperfections on autonomous safety monitoring using data from location-aware sensors, which provides the most important information for the autonomous jobsite safety monitoring system. The rest of this paper is organized as follows: The Related Work section summarizes the location-aware jobsite safety monitoring applications in construction and the imperfect data collected from sensors. The Research Approach section describes the research approach, including the testbed used for data collection, the test case used to evaluate the impacts of imperfect data on autonomous safety monitoring and the process of how the data is used to evaluate the impacts. The Preliminary Results section reports the preliminary results of the impacts on autonomous safety monitoring. Finally, the Conclusion section summarizes the results and proposes future research suggestions.

Keywords
Safety, Accidents, Data collection, Occupational safety, Diseases, Probe instruments, Building information modeling, Construction sites

Exploring Approaches to Improve the Performance of Autonomous Crane Safety Monitoring with Imperfect Data in Location-aware Wireless Sensor Networks

Conference paper
Luo, X., O’Brien, W.J., Leite, F., Goulet, J.
2013 European Group of Intelligent Computing in Engineering (EG-ICE) Workshop on Intelligent Computing in Engineering. Vienna, Austria. 10 pages

What is a Safe Working Zone? Designing Proactive Fall Prevention for Autonomous Monitoring

Conference paper
Luo, X., O’Brien, W.J., Leite, F.
2011 European Group of Intelligent Computing in Engineering (EG-ICE) Workshop on Intelligent Computing in Engineering. Enschede, the Netherlands. 7 pages.

Abstract

Falling from height is one of the major causes of fatalities in construction industry. The advancement and recent deployment of various sensing and mobile computing technologies on construction jobsite has provided an opportunity to achieve an autonomous safety monitoring system to prevent falling from height and hence improve safety performance of the industry. This paper presents the preliminary result of the first stage of the research on our envisioned autonomous safety monitoring system. In the paper, the authors defined the dynamic safe working zone model and its parameter determination. The safety knowledge introduced in this paper can serves as the foundation of actual system design and implementation.

Requirements for Autonomous Crane Safety Monitoring

Conference paper
Luo, X., Leite, F., O’Brien, W.J.
International Workshop on Computing in Civil Engineering 2011, Miami, FL, USA. 8 pages.

Abstract
Crane related accidents, caused by multiple factors such as a worker entering a dangerous area, is one of the major accident types in the construction industry. A vision for addressing this problem is through an intelligent jobsite, fully wired and sensed. Recent advancement in pervasive and ubiquitous computing makes autonomous crane safety monitoring possible. An initial step towards implementing autonomous crane safety monitoring is to identify the safety and information requirements needed. This paper presents a literature review and results from a set of expert interviews, used to extract requirements for autonomous crane safety monitoring. The extracted requirements for dynamic safety zones and associated information requirements as a precursor to deployment are also presented in the paper.

Keywords
Safety, Labor, Construction industry, Construction management, Cranes, Occupational safety

Information Requirements of a Generalized Framework for Jobsite Decision Making: Elicitation through Scenario Development

Conference paper
Luo, X., Leite, F., O’Brien, W.J.
8th European Conference on Product & Process Modeling 2010

Evaluation of Localization Techniques for the Construction Jobsite

Conference paper
Luo, X., O’Brien, W.J., Julien, C.
13th European Group for Intelligent Computing in Engineering (EG-ICE) Workshop on Intelligent Computing in Engineering and Architecture 2009. Berlin, German

An overview of carbon sequestration of green roofs in urban areas

Journal paper
Muhammad Shafique, Xiaolong Xue, XiaoweiLuo
Urban Forestry & Urban Greening, Volume 47, 2020,

Abstract

In urban areas, one way of mitigating the adverse effects of air pollution is the sustainable rooftop practice known as green roofs. How green roofs can help reduce carbon emissions in urban areas, directly and indirectly, is the focus of this review, which draws on recently published studies. The direct impact of green roofs on carbon sequestration involves vegetation and soil media, which can capture and store air pollutants on a building scale. The indirect impact includes the long-term green roof effect, which can include reducing building energy consumption, leading to a reduction in fossil fuel consumption. Consequently, this process could reduce CO2 emissions around the globe. According to the literature analysis, the indirect long-term benefits help promote green roofs as a green practice around the world. It was found that vegetation and soil properties are the key factors affecting the performance of building energy consumption reduction and CO2 sequestration. Stakeholders and the public are encouraged, based on the literature review results, to adopt green roofs in building construction projects as a climate mitigation strategy.

Keywords

Carbon emission reduction, Carbon sequestration, Direct impact, Green roofs (GRs), Indirect impact

A study on passengers’ alighting and boarding process at metro platform by computer simulation

Journal paper
Zitong Li, S.M.Lo, Jian Ma, Xiaowei Luo
Transportation Research Part A: Policy and Practice, Volume 132, February 2020, Pages 840-854

Abstract

Passengers’ alighting and boarding process in metro stations has attracted increasing research attention since it has significant influence on the platform passenger distribution as well as the train dwell time. In this study, a field survey was firstly performed in a densely populated metro station at downtown area in Hong Kong to observe passengers’ alighting and boarding characteristics and collect sample data. One commonly existing phenomenon is found that boarding passengers start to get aboard even when there are alighting passengers still inside the metro carriage. This is defined as passengers’ non-compliance behaviors in this paper. In addition, time indicators are defined to measure the alighting and boarding efficiency. Then a microscopic pedestrian simulation model based on the Social Force Model is proposed to simulate the passengers’ alighting and boarding patterns at metro platform. The verification result shows the good applicability of the proposed model to simulate the actual situation. Finally, several simulation tests are conducted to explore the impacts that passengers’ non-compliance behaviors have on the alighting and boarding efficiency in different passenger volume conditions. The simulation result shows that higher level of passengers’ non-compliance behaviors leads to longer passenger’s alighting duration and boarding duration, but the influence on the overall transaction time is related to different passenger volume conditions. Thus, metro station facility could apply different alighting and boarding rules in different passenger volume conditions to increase alighting and boarding efficiency.

Keywords

Pedestrian simulation, Alighting and boarding, Passenger behaviors, Metro stations

Multi-objective Decision-Making for the Ecological Operation of Built Reservoirs Based on the Improved Comprehensive Fuzzy Evaluation Method

Journal paper
Liu, B., Zhang, F., Wan, W., Luo, X.
Water Resources Management. September 2019, Volume 33, Issue 11, pp 3949–3964

Abstract

With the social progress and economic development, people have put forward requirements for the ecological operation of built reservoirs. However, there are conflicts between the ecological landscape and the existing benefits such as irrigation and flood control, so it is necessary to build a decision-making model for the comprehensive value of the ecological operation of reservoirs. Taking a reservoir project which needs to satisfy multi-objective requirements as an example, this paper proposes a set of decision-making methods for ecological operation of built reservoirs based on improved comprehensive fuzzy comprehensive evaluation method and constructs a multi-objective decision-making model and optimization strategy combination. Through case analysis in this paper, the improved comprehensive fuzzy evaluation method has a good effect on multi-objective decision-making of ecological dispatching of built reservoirs. The research shows that the combination strategy of improving the reservoir’s water storage capacity and the water-saving supporting transformation measures has a good effect, which can reduce the waste of the reservoir diversion project and large-scale high-efficiency water-saving transformation project construction. It embodies the idea of water-saving priorities and space balance and has broad application prospects in the optimization of reservoir ecological dispatch.

Keywords
Constructed reservoir; Ecological dispatching; Improved comprehensive fuzzy evaluation method; Multi-objective decision making; Optimization strategy

Built environment and management: exploring grand challenges and management issues in built environment

Journal paper
Wang, L., Xue, X., Yang, RJ., Luo, X., Zhao, H.
Frontiers of Engineering Management, September 2019, Volume 6, Issue 3, pp 313–326

Abstract
Engineering management research objects have gradually been transformed from micro-scale projects to macro-scale built environment. Built environment has driven the advancement of civilization through human history. From the Stone Age to the modern era, built environment, which refers to manmade surroundings, has provided the setting for human activities. Built environment has undergone developments and evolution processes as civilization grew. Today, technological advancements cause influences of built environment to encompass every aspect of life, as material, spatial and cultural products of the human labor force, which combines material factors and energy in a lively way of work and in forms. However, the concept of built environment remains unclear. Built environment faces a major challenge, such as the use of science and technology to solve key national and global issues. Thus, the definitions of built environment were systematically reviewed and summarized from different perspectives and levels to address these issues. The grand challenges of built environment, including climate change and energy consumption, urbanization and infrastructure construction, growth, and innovation, were summarized. Furthermore, the corresponding management issues and future development strategies were proposed to solve identified challenges of built environment.

Keywords
built environment; innovation; sustainability; resilience; urbanization; digitalization; infrastructure

A New Framework of Industrialized Construction Method in China: Towards On-Site Industrialization

Journal paper
Li, L., Li, Z., Li, X., Zhang, S., Luo, X.
Journal of Cleaner Production

Abstract
Many countries and regions consider industrialized construction to be a cleaner production method that facilitates sustainability in the construction industry. In China, proponents of industrialized construction have paid more attention to environmental and social sustainability, but the obstacles to economic sustainability have not been well solved. This study proposes a new industrialized construction method, OSI (On-Site Industrialization). OSI combines the advantages of prefabrication and cast-in-situ, and, to develop and validate the OSI framework, this work conducts two-phase action research. Based on the holistic overview of industrialized construction, the OSI framework was developed in action research phase 1. This framework includes five basic industrialized principles—standardization, prefabrication, modularization, lean, and sustainability. To evaluate the sustainability performance of OSI from the perspective of triple-bottom-line (TBL), the research team carried out a multiple-case study in action research phase 2. To validate the OSI framework, the research team used the conventional precast concrete construction for benchmarking. The findings indicate that OSI is a feasible industrialized construction method to balance the three dimensions of TBL in the Chinese construction industry. This research extends the theoretical knowledge body of industrialized construction while at the same time solving some practical problems in the construction industry.

Keywords
Industrialized construction; on-site industrialization; action research; high-rise concrete residential buildings; sustainability

 

New media data-driven measurement for the development level of prefabricated construction in China

Journal paper
4. Dou, Y., Xue, X., Wang, Y., Luo, X., Shang, S.
Journal of Cleaner Production, Volume 241, 20 December 2019, 118353

Abstract
Prefabricated construction (PC) is an effective approach for addressing the unsustainability issues of conventional construction methods. Despite considerable concern from the China’s government, the provincial development level of PC remains unclear. Lacking PC-related statistics hinders relevant research, while data obtained from new media (such as Weibo and WeChat) using web crawler can bridge this gap. This study proposed a new media-driven measurement for the development level of PC, targeting 31 provinces in China. A total of 28 alternative indexes were firstly selected based on the Politics-Economy-Society-Technology (PEST) analysis model, and the final 15 indexes were filtered through expert scoring and new media data-driven methods. Then, web crawling and text segmentation by Python were employed to acquire index data, supplemented by statistics. The indexes weights were determined through expert scoring and a cloud model. The quantitative measurement of the development level of PC was finally performed. The results mainly indicate the holistic development level of PC in China is currently low and its regional distribution is uneven, with high scores in the eastern provinces, and the western and northwestern provinces lagging behind The measurement system construction and the measurement index quantification driven by new media data in this study represent breakthroughs over traditional methods that rely on statistics, cases or questionnaires, which can be applied to other research fields. In addition, the measurement system constructed provides a reference to measure the PC development level in other countries.

Keywords
China; Development level; New media data; Prefabricated construction (PC)

Modeling city-scale building energy dynamics through inter-connected distributed adjacency blocks

Journal paper
Ma, R., Geng, C., Yu, Z., Chen, J., Luo, X..
Energy and Buildings, Volume 202, 1 November 2019, 109391

Abstract
Buildings consume the largest amount of energy in cities and simulating urban energy dynamics provides the most cost-effective references for urban building planning and energy policy-making. However, cities have a tremendous number of buildings and complicated physical/environmental conditions, current simulation models require formidable computation resources and time. This paper proposes a rapid simulation approach that decomposes city model into spatially correlated building blocks for distributed simulation. The proposed distributed adjacency blocks (DABs) algorithm utilizes 2D footprint to construct 3D building groups and solar azimuth angles, altitude angles, and shading plane to simplify simulation targets. With the proposed method, the energy dynamics of the whole city can be simulated in parallel with multiple threads through abstracting inter-building boundary conditions. To validate the proposed method, this study conducted two validation experiments with different building numbers, window-to-wall ratio, and climate conditions. The simulation results suggested that the proposed algorithm can dramatically improve the simulation efficiency and generate less than 5% of percentage difference compared with the conventional whole city simulation approaches.

Keywords
City-scale building simulation; Urban energy dynamics; Inter-building effects; Building networks

Direction-adaptive energy harvesting with a guide wing under flow-induced oscillations

Journal paper
Gong, Y., Shan, X., Luo, X., Pan, J., Xie, T., Yang, Z.
Energy, Volume 187, 15 November 2019, 115983

Abstract
Ocean, as a natural system containing a tremendous amount of energy, can be used for either the large-scale power grid network or small-scale distributed off-grid electronic devices via the energy harvesting technology. As one low-cost and effective way to capture flow energy, the vortex induced vibration (VIV) energy harvesting is attracting more and more attention. However, the direction of water flow in a natural water environment is changeable while most existing VIV harvesters are limited by their directional sensitivity. These harvesters only respond to flow excitations from one fixed direction and become insufficient once the flow direction varies. In this paper, we take the lead to address the unidirectional sensitivity issue and propose a novel direction-adaptive energy harvester. We establish theoretical models to analyze the Kármán vortex street, the torque excitation, and the vortex-induced pressure oscillations. Prototypes are fabricated and tested to characterize the direction-adaptive capability of the proposed design under different flow conditions. The experiments demonstrate that the energy harvesting angle span is extended by the guide wing from 40° to 360° under a wide flow velocity range. The guide-wing method endows harvesters with an all-around multidirectional sensitivity, and thus will accelerate energy harvesters’ applications in oceans.

Keywords
Energy harvester; Piezoelectric; Vortex shedding; Directional sensitivity; Vibration

Nanotechnology in Transportation Vehicles: An Overview of Its Applications, Environmental, Health and Safety Concerns

Journal paper
Muhammud, S., Luo, X.
Materials 2019, 12, 2493

Abstract
Nanotechnology has received increasing attention and is being applied in the transportation vehicle field. With their unique physical and chemical characteristics, nanomaterials can significantly enhance the safety and durability of transportation vehicles. This paper reviews the state-of-the-art of nanotechnology and how this technology can be applied in improving the comfort, safety, and speed of transportation vehicles. Moreover, this paper systematically examines the recent developments and applications of nanotechnology in the transportation vehicle industry, including nano-coatings, nano filters, carbon black for tires, nanoparticles for engine performance enchantment and fuel consumption reduction. Also, it introduces the main challenges for broader applications, such as environmental, health and safety concerns. Since several nanomaterials have shown tremendous performance and have been theoretically researched, they can be potential candidates for applications in future environmental friendly transportation vehicles. This paper will contribute to further sustainable research and greater potential applications of environmentally friendly nanomaterials in healthier transportation vehicles to improve the transportation industry around the globe.

Keywords
nanotechnology; transportation vehicles; environmental concerns; human health; safety management

Parallel computational building-chain model for rapid urban-scale energy simulation

Journal paper
Zheng, Z., Chen, J., Luo, X.
Energy and Buildings, Volume 201, 15 October 2019, Pages 37-52

Abstract
As buildings consume substantial amounts of energy, researchers and decision makers are giving more attention to urban-scale energy assessment and design. In fact, researchers have developed many building-energy modeling and simulation tools that are regarded as effective for building designers and facility managers. However, few models have been found suitable for urban-scale efficient building design and planning. Indeed, to carry out urban-scale energy modeling and simulation, it is necessary to possess a comprehensive understanding of interactions among building groups as well as huge computational resources. To develop a more efficient and reliable simulation model, this study proposes a parallel computational building-chain (PCBC) model. This PCBC model aims to simplify building interactions and implement efficient multi-thread computations. It can decompose large-scale building groups into inter-connected building units by defining the thermal and shading boundary conditions of buildings in a neighborhood. By coupling individual buildings’ simulated energy consumption, the urban energy dynamics can be reconstructed. To validate the proposed method, researchers examined a sample urban-building group with 410 buildings. Compared with the conventional integrated Whole City model, the proposed method achieved nearly the same outputs with reduced computation time. With an increase in the simulation scale, computational efficiency can be improved in the future.

Keywords
Urban-scale energy simulation; Parallel computation; Building group decomposition; Urban energy dynamics

An Automatic Literature Knowledge Graph and Reasoning Network Modelling Framework Based on Ontology and Natural Language Processing

Journal paper
Chen, H., Luo, X.
Advanced Engineering Informatics, Volume 42, October 2019, 100959

Abstract
With the advancement of scientific and engineering research, a huge number of academic literature are accumulated. Manually reviewing the existing literature is the main way to explore embedded knowledge, and the process is quite time-consuming and labor intensive. As the quantity of literature is increasing exponentially, it would be more difficult to cover all aspects of the literature using the traditional manual review approach. To overcome this drawback, bibliometric analysis is used to analyze the current situation and trend of a specific research field. In the bibliometric analysis, only a few key phrases (e.g., authors, publishers, journals, and citations) are usually used as the inputs for analysis. Information other than those phrases is not extracted for analysis, while that neglected information (e.g., abstract) might provide more detailed knowledge in the article. To tackle with this problem, this study proposed an automatic literature knowledge graph and reasoning network modeling framework based on ontology and Natural Language Processing (NLP), to facilitate the efficient knowledge exploration from literature abstract. In this framework, a representation ontology is proposed to characterize the literature abstract data into four knowledge elements (background, objectives, solutions, and findings), and NLP technology is used to extract the ontology instances from the abstract automatically. Based on the representation ontology, a four-space integrated knowledge graph is built using NLP technology. Then, reasoning network is generated according to the reasoning mechanism defined in the proposed ontology model. To validate the proposed framework, a case study is conducted to analyze the literature in the field of construction management. The case study proves that the proposed ontology model can be used to represent the knowledge embedded in the literatures’ abstracts, and the ontology elements can be automatically extracted by NLP models. The proposed framework can be an enhancement for the bibliometric analysis to explore more knowledge from the literature.

Keywords
Representation ontology; Natural language processing; Knowledge graph; Knowledge reasoning

A Kalman filter-based bottom-up approach for household short-term load forecast

Journal paper
Zheng, Z., Chen, H., Luo, X.
Applied Energy, Volume 250, 15 September 2019, Pages 882-894

Abstract
Renewable energy sources are now being used with buildings like PV panels. Consequently, short-term household load forecast plays an important role in managing distributed energy generation, local consumption, and grid-building integration. Forecasting household load, however, can be an intractable problem. These loads are characterized by large uncertainty and variations, leaving much room to improve accuracy. To improve the household load forecast accuracy, this paper advocates a Kalman filter-based bottom-up approach. First, using a deep learning model and a persistence model on public datasets, the authors verified the advantage of the bottom-up approach through granularity analysis at the appliance, room, house levels. Employing the Symmetric Mean Absolute Percentage Error, the authors compared two strategies: (1) the conventional strategy, which forecasts the load directly at the household level, and (2) the bottom-up strategy, which aggregates the forecasts made at the room or appliance level. Experimental results on public datasets demonstrated that the bottom-up approach holds great promise. Second, as the bottom-up approach is often criticized for the cost, the authors designed a recontextualized Kalman filter model to efficiently forecast appliance energy usages. Using two strategies, the authors compared the Kalman filter-based bottom-up approach with deep-learning models. They found the bottom-up approach reduced forecast errors 49% more than the deep-learning models and 47% more than the conventional strategy. Finally, the authors concluded that a Kalman filter-based bottom-up approach could efficiently improve household load forecast accuracy. The findings could help give fast and accurate load forecasts for building energy management and predictive controls.

Keywords
Household load forecast; Bottom-up approach; Forecast granularity; Appliance usage forecast; Kalman filter model

Collecting building occupancy data of high resolution based on WiFi and BLE network

Journal paper
Chen, J., Chen, H., Luo, X.
Automation in Construction, Volume 102, June 2019, Pages 183-194

Abstract
Building occupancy information is the premise of modern building service systems’ control and energy conservation. Inaccurate occupancy information could result in a low comfort level and an energy waste. Existing occupancy detecting system relies on indirect and low-resolution environmental sensors, which potentially mislead facility managers and result in inefficiency in building energy use. In this study, the authors proposed a novel occupancy detection approach through a coupled indoor positioning system. The system integrates conventional k-nearest neighbor positioning algorithm and stochastic random walk algorithm to collect high-resolution occupancy data through Wi-Fi and Bluetooth Low Energy (BLE) networks. The proposed system is able to identify the meshed geospatial distribution of occupants, and to future track their movements in a network covered space. The detected occupancy meshes are suitable for direct implementation in building facility management since their operation is based on thermal zones rather than occupants’ coordinates. To validate the feasibility and accuracy of the proposed system, the authors conducted a preliminary experiment in an institutional building. By comparing the positioning distance measurement metrics and matching parameters, the authors found the occupancy information detected by the proposed model is highly precise, accurate and reliable for the application in the building energy management.

Keywords
Building occupant localization; Zone-based; Building energy system; kNN; Stochastic random walk

A Proactive Workers’ Safety Risk Evaluation Framework based on Position and Posture Data Fusion

Journal paper
Chen, H., Ke, J., Zheng, Z., Luo, X.
Automation in Construction, Volume 98, February 2019, Pages 275-288

Abstract
Construction workers’ safety risk evaluation mainly relies on manual observation with safety expert’s experience. The manual process is labor intensive and time-consuming. A proactive workers’ safety risk evaluation framework is needed to handle this issue. In this paper, the position and posture have been identified as the two key quantitative features, and a position and posture fusion principle is proposed for the evaluation of construction workers’ behaviors safety risks. Three participants are invited to involve in the indoor construction activities with working at height three times, and the participants’ locations, postures, and video are recorded using sensing devices. The participants’ risk levels are evaluated based on posture, location, and posture-location fusion respectively. A comparison of the risk level evaluated based on those three approaches and the ground truth provided by the experts. The results show that the accuracy of automatic safety risk level evaluation based on location and posture fusion is 83%, compared with 81% and 57% achieved by the single-feature based risk level evaluation using location and posture respectively. Thus, the position and posture fusion-based evaluation is more reliable in real situations.

Keywords
Data fusion; Construction safety; Localization; Posture detection; Indoor localization

Exploring the Quantitative Impact of Localization Accuracy on Localization-based Safety Monitoring’s Performance on Construction Jobsite

Journal paper
Chen, H., Luo, X.
Journal of Computing in Civil Engineering, Volume 33 Issue 6 - November 2019

Abstract
The construction industry continues to be one of the industries with the highest accident rate. With the recent advancement of computing and sensing technologies, more efforts have been made in the field of context-aware autonomous job site monitoring, which can automatically track and evaluate the worker’s behavior and job site conditions in real time to issue warnings for unsafe behaviors and conditions on sites. The location of an entity (e.g., worker, equipment, or material) is one of the core information for context-aware management. Therefore, a large number of recent studies focus on exploring different approaches to improve the localization technologies’ accuracy, robustness, and convenience of deployment. However, systematic knowledge is missing on how the localization algorithm’s accuracy affects the construction safety monitoring’s performance. To quantify the impact in this paper, first, a localization system accuracy model and three safety clearance models are proposed as the base. Second, a Monte Carlo simulation model is designed as an abstract representation for localization systems. By conducting the simulation, the effects of the localization errors on safety monitoring performance are quantitatively analyzed. A case of a tower crane scenario is investigated as a demonstration. With the simulation data, a regression model is established, indicating that the precision and recall of the location-based safety decision making are not only related to the accuracy of the localization system but also related to the size of the safety zones. With the proposed model, the impacts of a given localization system on the location-based safety decision making can be quantified without the actual deployment, offering a more straightforward evaluation tool of the localization system.

Keywords:
Safety, Site investigation, Construction management, Errors (statistics), Simulation models, Information management, Occupational safety, Model accuracy

Fusion Model for Hazard Association Network Development: A Case in Elevator Installation and Maintenance

Journal paper
Liao, P., Chen, H., Luo, X.
KSCE Journal of Civil Engineering, April 2019, Volume 23, Issue 4, pp 1451–1465

Abstract
This paper proposes a fusion model for developing a data-driven risk association network, based on historical inspection records. The fusion model first re-categorizes the hazards based on the similarity in their occurrence patterns. Second, spatial and temporal heterogeneity of the hazard occurrence is examined, after which site-specific records as outliers are removed from the database. Third, a structured learning approach is used to investigate the causal relations between safety risks and the weight of each relation is calculated based on the association rules. Finally, the causal relations and weightings are fused to form the hazard association network, based on which critical hazards can be identified for safety management strategy planning. Safety management for an elevator installation and maintenance is used as a domain to validate the proposed fusion model, which develops the hazard association network using a dataset with 110,698 safety inspection records on 25,729 sites (with elevator installation or maintenance) managed by an elevator company. Using the developed network, critical hazards on the sites are identified for proactive construction management.

Keywords
safety inspection; data mining; real-time association rules; hazard association network; data fusion; hazard pattern; proactive safety

Comparative analysis of U-pipe location on the sizing of borehole heat exchangers

Journal paper
Zhang, L., Zhang, Q., Luo, X., Huang, G.
Applied Thermal Engineering, Volume 150, 5 March 2019, Pages 666-673

Abstract
The geometry of borehole heat exchangers (BHEs) is important for their sizing. In practice, a U-pipe can be located anywhere inside a borehole. To simplify the BHE modeling, ASHRAE has two standardized borehole geometries (the B type and BC type borehole geometry). In general, the B type is hard to achieve, although it is widely used in current BHE sizing. The BC type is the one that most likely occurs in practice, but there is a lack of detailed studies. This study presents a comparative analysis of the effects of U-pipe locations on BHE sizing. As current models are only feasible for the B type, a model for the BC type is first developed and verified using the well-known Sandbox experiment developed by Beier. Then, a comparative study of the B and BC types is conducted using the borehole depth and investment costs of a real office building. Finally, the factors influencing the borehole depth differences of the B or BC types are discussed, and guidelines for future BHE sizing are suggested.

Keywords
Borehole heat exchangers; U-pipe locations; BHE sizing; Fluid temperature prediction; Investment costs