A Hybrid PSO–SVM Model Based on Safety Risk Prediction for the Design Process in Metro Station Construction

Incorporating safety risk into the design process is one of the most effective design sciences to enhance the safety of metro station construction. In such a case, the concept of Design for Safety (DFS) has attracted much attention. However, most of the current research overlooks the risk-prediction process in the application of DFS. Therefore, this paper proposes a hybrid risk-prediction framework to enhance the effectiveness of DFS in practice. Firstly, 12 influencing factors related to the safety risk of metro construction are identified by adopting the literature review method and code of construction safety management analysis. Then, a structured interview is used to collect safety risk cases of metro construction projects. Next, a developed support vector machine (SVM) model based on particle swarm optimization (PSO) is presented to predict the safety risk in metro construction, in which the multi-class SVM prediction model with an improved binary tree is designed. The results show that the average accuracy of the test sets is 85.26%, and the PSO–SVM model has a high predictive accuracy for non-linear relationship and small samples. The results show that the average accuracy of the test sets is 85.26%, and the PSO–SVM model has a high predictive accuracy for non-linear relationship and small samples. Finally, the proposed framework is applied to a case study of metro station construction. The prediction results show the PSO–SVM model is applicable and reasonable for safety risk prediction. This research also identifies the most important influencing factors to reduce the safety risk of metro station construction, which provides a guideline for the safety risk prediction of metro construction for design process.

[1]  Herbert A. Simon,et al.  Scientific discovery and inventive engineering design: cognitive and computational similarities , 2001 .

[2]  Ning-Ning Feng,et al.  Study on Vibration Reduction Method for a Subway Station in Soft Ground , 2017 .

[3]  Yanan Yu,et al.  A Prediction of Precipitation Data Based on Support Vector Machine and Particle Swarm Optimization (PSO-SVM) Algorithms , 2017, Algorithms.

[4]  Jimmie Hinze,et al.  Viability of Designing for Construction Worker Safety , 2005 .

[5]  H A SIMON,et al.  HUMAN ACQUISITION OF CONCEPTS FOR SEQUENTIAL PATTERNS. , 1963, Psychological review.

[6]  Ying Cao,et al.  Application of time series analysis and PSO–SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China , 2016 .

[7]  Zhou Wei,et al.  Safety risk factors of metro tunnel construction in China: An integrated study with EFA and SEM , 2018, Safety Science.

[8]  Xin Zheng,et al.  Metro Construction Safety Risk Assessment Based on the Fuzzy AHP and the Comprehensive Evaluation Method , 2014 .

[9]  Sathyanarayanan Rajendran,et al.  Design’s role in construction accident causality and prevention: Perspectives from an expert panel , 2008 .

[10]  Jochen Teizer,et al.  Ontology-based semantic modeling of construction safety knowledge: Towards automated safety planning for job hazard analysis (JHA) , 2015 .

[11]  Steve Rowlinson,et al.  Capturing Safety Knowledge Using Design-for-Safety-Process Tool , 2004 .

[12]  Liangliang Song,et al.  Using Interpretative Structural Modeling to Identify Critical Success Factors for Safety Management in Subway Construction: A China Study , 2018, International journal of environmental research and public health.

[13]  T. Michael Toole.  Increasing Engineers' Role in Construction Safety: Opportunities and Barriers , 2005 .

[14]  Shao-hui Peng,et al.  Sand-layer collapse treatment: An engineering example from Qingdao Metro subway tunnel , 2018, Journal of Cleaner Production.

[15]  Yuhong Wang,et al.  Machine Learning Methods to Predict Social Media Disaster Rumor Refuters , 2019, International journal of environmental research and public health.

[16]  Zhang Dingli,et al.  Types and Characteristics of Safety Accidents Induced by Metro Construction , 2009, 2009 International Conference on Information Management, Innovation Management and Industrial Engineering.

[17]  Nashwan Dawood,et al.  Development of workspace conflict visualization system using 4D object of work schedule , 2014, Adv. Eng. Informatics.

[18]  John A. Gambatese,et al.  Liability in Designing for Construction Worker Safety , 1998 .

[19]  Salvatore T. March,et al.  Design and natural science research on information technology , 1995, Decis. Support Syst..

[20]  Shixia Duan,et al.  Study on the Influencing Factors of Urban Subway Engineering Construction Safety , 2018 .

[21]  Sid Ghosh,et al.  Identifying and assessing the critical risk factors in an underground rail project in Thailand: a factor analysis approach , 2004 .

[22]  王向前,et al.  A Study on Risk Prediction Model of Coal Enterprise Safety Management-Based on RS-SVM , 2014 .

[23]  Moussa S. Elbisy,et al.  Sea Wave Parameters Prediction by Support Vector Machine Using a Genetic Algorithm , 2013 .

[24]  John A. Gambatese,et al.  Can Design Improve Construction Safety?: Assessing the Impact of a Collaborative Safety-in-Design Process , 2005 .

[25]  Qihu Qian,et al.  Safety risk management of underground engineering in China: Progress, challenges and strategies , 2016 .

[26]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[27]  H. Simon,et al.  The sciences of the artificial (3rd ed.) , 1996 .

[28]  P. J. García Nieto,et al.  Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability , 2015, Reliab. Eng. Syst. Saf..

[29]  Miroslaw J. Skibniewski,et al.  Validating DFS concept in lifecycle subway projects in China based on incident case analysis and network analysis , 2018 .

[30]  Charles M. Eastman,et al.  BIM-based fall hazard identification and prevention in construction safety planning , 2015 .

[31]  Xianguo Wu,et al.  Safety risk identification system for metro construction on the basis of construction drawings , 2012 .

[32]  D E Pickbourne.  Design for safety. , 1967, Chemistry & industry.

[33]  Daniel Cahill Hansen.  Measuring and Improving Designer Hazard Recognition Skill , 2015 .

[34]  Leonhard Blesius,et al.  Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers , 2016, Remote. Sens..

[35]  J. G. F. Coutinho,et al.  An aspect-oriented approach for designing safety-critical systems , 2013, 2013 IEEE Aerospace Conference.

[36]  Thanet Aksorn,et al.  Critical success factors influencing safety program performance in Thai construction projects , 2008 .

[37]  Dongil Shin,et al.  Design and implementation of an integrated safety management system for compressed natural gas stations using ubiquitous sensor network , 2014, Korean Journal of Chemical Engineering.

[38]  Yang Miang Goh,et al.  Design-for-Safety knowledge library for BIM-integrated safety risk reviews , 2018, Automation in Construction.

[39]  Shuqiang Wang,et al.  A GA-based feature selection and parameter optimization for support tucker machine , 2017 .

[40]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[41]  Yong K. Cho,et al.  Integrating work sequences and temporary structures into safety planning: Automated scaffolding-related safety hazard identification and prevention in BIM , 2016 .

[42]  John Gambatese,et al.  The trajectories of Prevention through Design in construction. , 2008, Journal of safety research.

[43]  Erik Hollnagel,et al.  Risk + barriers = safety? , 2008 .

[44]  Q Z Yu,et al.  Analysis of factors influencing safety management for metro construction in China. , 2014, Accident; analysis and prevention.

[45]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[46]  Zhifang Zhou,et al.  A carbon risk prediction model for Chinese heavy-polluting industrial enterprises based on support vector machine , 2016 .

[47]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[48]  Abid Yahya,et al.  A New Design for a Motorway Surveillance System Using a Wireless Ad-Hoc Camera Network to Improve Safety , 2014 .

[49]  A R Duff,et al.  Contributing factors in construction accidents. , 2005, Applied ergonomics.

[50]  John A. Gambatese,et al.  Tool to design for construction worker safety , 1997 .

[51]  Børge Rokseth,et al.  Applications of machine learning methods for engineering risk assessment – A review , 2020, Safety Science.

[52]  Alexander M. Zemliak.  Analog system design problem formulation on the basis of control theory , 2001, ICECS 2001. 8th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.01EX483).

[53]  Jun Wang,et al.  Geotechnical and safety protective equipment planning using range point cloud data and rule checking in building information modeling , 2015 .

[54]  Jimmie Hinze,et al.  Addressing construction worker safety in the design phase: Designing for construction worker safety , 1999 .

[55]  Michael Behm,et al.  Linking construction fatalities to the design for construction safety concept , 2005 .

[56]  Haofeng Xing,et al.  Effects of Pit Excavation on an Existing Subway Station and Preventive Measures , 2016 .

[57]  Hong-yu Zhang,et al.  A hybrid PSO-SVM model based on clustering algorithm for short-term atmospheric pollutant concentration forecasting , 2019, Technological Forecasting and Social Change.

[58]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[59]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[60]  Cong Chen.  Numerical analysis of influence of deep excavations on metro tunnel , 2016 .

[61]  Matthew R. Hallowell,et al.  Prevention through design and construction safety management strategies for high performance sustainable building construction , 2012 .

[62]  Miroslaw J. Skibniewski,et al.  Dynamic risk analysis for adjacent buildings in tunneling environments: a Bayesian network based approach , 2015, Stochastic Environmental Research and Risk Assessment.

[63]  Michael Behm,et al.  Safe Design Suggestions for Vegetated Roofs , 2012 .

[64]  Il Moon,et al.  Automatic verification of control logics in safety instrumented system design for chemical process industry , 2009 .

[65]  Zhongxing Zhang,et al.  Research on Fault Diagnosis of Diesel Engine Based on PSO-SVM , 2016 .

[66]  Li Yan,et al.  BIM and Safety Rules Based Automated Identification of Unsafe Design Factors in Construction , 2016 .

[67]  Göran Goldkuhl,et al.  DESIGN THEORIES IN INFORMATION SYSTEMS - A NEED FOR MULTI-GROUNDING , 2004 .

[68]  Jongwon Seo,et al.  Risk-Based Safety Impact Assessment Methodology for Underground Construction Projects in Korea , 2008 .

[69]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[70]  Meng Li,et al.  Methodologies of safety risk control for China’s metro construction based on BIM , 2018, Safety Science.

[71]  Heng Li,et al.  Computer vision aided inspection on falling prevention measures for steeplejacks in an aerial environment , 2018, Automation in Construction.

[72]  A. Roy Duff,et al.  Development of Causal Model of Construction Accident Causation , 2001 .

[73]  Zhu Hong-ping.  Research on Pattern Recognition of Gas Explosion Disaster Risk in Coal Mines Based on PSO-SVM , 2013 .

[74]  Alan R. Hevner,et al.  Design Science in Information Systems Research , 2004, MIS Q..

[75]  Matthew R. Hallowell,et al.  Measuring and improving designer hazard recognition skill: Critical competency to enable prevention through design , 2016 .

[76]  Jieh-Haur Chen,et al.  Developing an SVM based risk hedging prediction model for construction material suppliers , 2010 .

[77]  Bong-Jin Yum,et al.  Robust Relevance Vector Machine With Variational Inference for Improving Virtual Metrology Accuracy , 2014, IEEE Transactions on Semiconductor Manufacturing.

[78]  Feng Zhao,et al.  Fault Diagnosis of Loader Gearbox Based on an ICA and SVM Algorithm , 2019, International journal of environmental research and public health.

[79]  Kuei-Chung Chang,et al.  Design and Implementation of Traffic Safety Guardian System for Android Based on OpenCV , 2012, 2012 International Conference on Connected Vehicles and Expo (ICCVE).

[80]  Guo-qing Zhu,et al.  Numerical Study on Transverse Temperature Distribution of Fire Zone in Metro Tunnel Fire , 2016 .

[81]  Haiyan Lu,et al.  Air Pollution Forecasts: An Overview , 2018, International journal of environmental research and public health.

[82]  Yuan Zhang,et al.  Priorization of River Restoration by Coupling Soil and Water Assessment Tool (SWAT) and Support Vector Machine (SVM) Models in the Taizi River Basin, Northern China , 2018, International journal of environmental research and public health.

[83]  Zhipeng Zhou,et al.  Accident prevention through design (PtD): Integration of building information modeling and PtD knowledge base , 2019, Automation in Construction.

[84]  Fred A Manuele,et al.  Prevention through Design (PtD): history and future. , 2008, Journal of safety research.

[85]  Weicheng Fan,et al.  Safety evaluation of engineering and construction projects in China , 2003 .