Fuzzy Rule-Based Evidential Reasoning Approach for Safety Analysis

Abstract

This paper aims at proposing a framework for modelling the safety of an engineering system with various types of uncertainties using a fuzzy rule-based evidential reasoning (FURBER) approach. In the framework, parameters used to define the safety level, including failure rate, failure consequence severity and failure consequence probability, are described using fuzzy linguistic variables; a fuzzy rule-base designed on the basis of a belief structure is used to capture uncertainty and non-linear relationships between these parameters and the safety level; and the inference of the rule-based system is implemented using the evidential reasoning algorithm. A numerical study of collision risk analysis for a kind of offshore platform is used to illustrate the application of the proposed approach.

Keywords:

• Safety analysis
• decision-making
• uncertainty
• fuzzy rule-base
• evidential reasoning

Acknowledgements

This work forms part of the projects supported by the UK Engineering and Physical Sciences Research Council (EPSRC) under Grant Numbers GR/R30624 and GR/R32413; The National Natural Science Foundation of China (NSFC) under the Grant No: 70171035, and the Fujian Natural Science Foundation under the Grant No: A0010002.

Notes

Jun Liu (B.Sc and M.Sc in Applied Mathematics in 1993 and 1996, respectively, and Ph.D. in Information Engineering and Control in 1999 from Southwest Jiaotong University, Chengdu, P.R. China) is currently a Postdoctoral Research Fellow in decision and system science at the Manchester School of Management of UMIST, Manchester, UK. Focusing research on algebraic and non-classical logic (many-valued logic, fuzzy logic), automated reasoning theory and methods, fuzziness and uncertainty theory and applications, intelligent decision support systems and evaluation analysis, information fusion and data combinations. His current applied research covers intelligent decision analysis and support under uncertainties for design decision-making, risk and safety analysis in engineering fields.

Jian-Bo Yang is Chair Professor of Decision and System Sciences at the Manchester School of Management (MSM) of UMIST, and is currently Head of the MSM Operations Management Group. He received his BEng and MEng degrees in Control Engineering at the North Western Polytechnic University, Xi'an, China in 1981 and 1984, respectively, and a Ph.D. degree in Systems Engineering at Shanghai Jiao Tong University, Shanghai, China in 1987. His current main research interests include intelligent decision analysis and support under uncertainties, multiobjective optimisation, system modelling, simulation and control with applications in both engineering and management systems.

Jin Wang is Professor of Marine Technology in the School of Engineering at Liverpool John Moores University. He received his BSc in Marine Automation from Dalian Maritime University, P. R. China, his M.Sc in Marine Engineering and Ph.D. (via staff registration) in Marine Safety Engineering from the University of Newcastle upon Tyne in 1989 and 1994, respectively. He has been involved in marine and offshore safety research for the past 13 years with support from the EPSRC, EU, HSE, etc. He is a member of the Council of the UK Safety and Reliability Society (SaRS) and the Technical Committee of the Institute of Marine Engineering, Science and Technology (IMarEST). He is also a Chartered Engineer (CEng) and a Fellow of the IMarEST. Professor Wang's major research interests include safety and reliability based design and operations of large marine and offshore systems, probabilistic and non-probabilistic safety analysis and decision making, port safety assessment and analysis of safety-critical systems in the software domain.

How Sing Sii obtained his Bachelor Degree in Mechanical Engineering from the University of South Australia, a Masters Degree in Engineering Science from the University of Malaya, Malaysia, and a Ph.D. Degree in Marine and Mechanical Engineering from Staffordshire University, UK. He is a Chartered Mechanical & Marine Engineer, a member of IMarEST and IMechE, and an associate member of UK SaRS. He has more than 15 years' industrial experience in various disciplines. Currently he is a Postdoctoral Research Fellow at Liverpool John Moores University working on an offshore safety research project funded by the UK EPSRC. He is also a safety consultant in the rail industry. His research and consultation interests are quality, reliability and safety engineering and management.

Ying-Ming Wang is a Professor of Management Sciences at the School of Public Administration of Fuzhou University in China. He received his BEng degree in Industrial Electric Automation from Jiangsu University of Science and Technology in 1984, his MEng and Ph.D. degrees both in Systems Engineering, respectively, from Huazhong University of Science and Technology in 1987 and Southeast University in 1991. Before joining Fuzhou University in June 2002, he was a Professor of Management Science at the School of Management of Xiamen University. His research interests include multiple attribute decision making (MADM), evidential reasoning (ER), analytic hierarchy process (AHP), data envelopment analysis (DEA), combined forecasting and rough sets (RS), etc.

^†[email protected]

^‡[email protected]

^¶[email protected]