Group risk assessment in failure mode and effects analysis using a hybrid probabilistic hesitant fuzzy linguistic MCDM method

• Published in: Expert systems with applications 2022-02, Vol.188, p.116013, Article 116013
• Main Authors: Wang, Zhi-Chao, Ran, Yan, Chen, Yifan, Yang, Xin, Zhang, Genbao
• Format: Article
• Language: English
• Subjects: Best-worst method; Decision making; Failure; Failure analysis; Failure mode and effects analysis; Failure modes; Fuzzy sets; Linguistics; Maximization; Multi-criteria decision making; Multiple criterion; Network analysis; Optimization; Probabilistic hesitant fuzzy linguistic term sets; Risk analysis; Risk assessment; Social network analysis; Social networks; System failures; TOPSIS
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2021.116013

•PHFLTSs are adopted to express epistemic uncertainty of group members for risk assessment.•MCDM methods by PHFLTSs namely SNA, MCM, BWM, MDM, and TOPSIS are used in the proposed FMEA model.•The subjective, objective and integrated weights of group members and risk factors are considered.•A case study with sensitive and comparative analyses is used toverify the proposed FMEA model. Failure mode and effects analysis (FMEA) usually requires multi-domain specialists to implement the group risk assessment for identifying and eliminating system failures. Therefore, this paper combines several multi-criteria decision making (MCDM) techniques with probabilistic hesitant fuzzy linguistic term sets (PHFLTSs) to implement risk assessment of failure modes by a panel of specialists. It aims at overcoming some defects existing in the conventional FMEA, such as without epistemic uncertainty and group risk assessment, as well as with some questions incurring from the risk priority number (RPN). Consequently, group members utilize PHFLTSs to express their subjective uncertain risk assessments on failure modes, in which the social network analysis (SNA) and maximizing consensus method (MCM) are exploited to derive the subjective and objective weights of group members respectively, afterwards their integrated weights are employed to aggregate individual risk assessments into the collective risk assessment. Additionally, the subjective and objective weights of risk factors are garnered by the best-worst method (BWM) and maximizing deviation method (MDM) separately, from which their integrated weights are incorporated into the technique for order preference by similarity to ideal solution (TOPSIS) so as to obtain the risk ranking of failure modes. Finally, an example with sensitive and comparative analyses is presented to demonstrate the effectiveness of the proposed approach.