An improved fuzzy inference system-based risk analysis approach with application to automotive production line

• Published in: Neural computing & applications 2020-07, Vol.32 (14), p.10573-10591
• Main Authors: Soltanali, Hamzeh, Rohani, Abbas, Tabasizadeh, Mohammad, Abbaspour-Fard, Mohammad Hossein, Parida, Aditya
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial Intelligence; Automobile industry; Automotive; Catastrophic failure analysis; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Diagnostic software; Diagnostic systems; Drift och underhållsteknik; Failure; Failure modes; Fuzzy logic; Fuzzy systems; Image Processing and Computer Vision; Industrial safety; Inference; Maintenance; Operation and Maintenance; Original Article; Parameter identification; Probability and Statistics in Computer Science; Reliability analysis; Risk analysis; Risk management; Sensitivity; Sensitivity analysis
• ISSN: 0941-0643; 1433-3058; 1433-3058
• DOI: 10.1007/s00521-019-04593-z

Reliability and safety in the process industries like automotive industry are important key success factors for upgrading availability and preventing catastrophic failures. In this context, failure mode and effect analysis (FMEA) technique is a proactive diagnostic tool for evaluating all failure modes which reduces the highest risk priority failures. However, it still suffers from subjective uncertainty and ambiguity which are important factors in risk analysis procedures. Hence, this paper provides a comprehensive survey to overcome the drawbacks of the traditional FMEA through improved FMEA, incorporating the fuzzy inference system (FIS) environment. For this purpose, the effective attributes, such as; various scales and rules, various membership functions, different defuzzification algorithms and their impacts on fuzzy RPN (FRPN) have been investigated. Moreover, three types of sensitivity analysis were performed to identify the effect and authority control of risk parameters, i.e., severity, occurrence and detection on FRPN. To demonstrate the feasibility of the proposed framework, as a practical example, the method was implemented in complex equipment in an automotive production line. The result of FIS-FMEA model revealed that the proposed framework could be useful in recognizing the failure modes with critical risk values compared to the traditional FMEA. Given the potential applications of this approach, suitable maintenance actions can be recommended to improve the reliability and safety of process industry, such as automotive production line.