A holistic failure modes and effects analysis for university plastic injection laboratory under Bayesian Network

University Research & Development (R&D) laboratories are facilities used for research and manufactur-ing activities in engineering and basic science fields. Various filling materials are used in plastic R&D laboratories to improve the mechanical properties of thermoplastics or to recycle waste materials. The use of filling materials causes changes in plastic production parameters. This study dealt with the risks arising from extrusion, injection and shredder in a plastic injection laboratory, which led to the inability to manufacture the appropriate product under a holistic methodology. The proposed holistic methodology merges the concepts of failure mode and effects analysis (FMEA), fuzzy best-worst method (FBWM), and a rule-based three-hierarchical Bayesian network (RB-THBN). First, 15 root risks have been identified under a three-stage hierarchy with the support of laboratory decision makers. Then, questionnaires were created using the FMEA concept. The importance values (degree of belief-DoB) of three different FMEA parameters (severity, occurrence and detection) by experts for each risk have been calculated with FBWM. And finally, the RB-THBN has been created, and the final risk values have been computed using the linear utility function for the network. The system has been analyzed via a Bayesian modeling software. A validity test and a control measures planning has also been executed. According to the results, the highest root risk has been determined as "E2-The prepared mixture is not homogeneous"with a crisp risk score of 0.639559. In addition, "Failure due to extrusion"has been determined as the highest risk category with a score of 0.564059. It was discussed in detail that these risks arise from homogenization and how the used mixture should be homogenized. A comparative study among traditional FMEA, FMEA extended under FBWM and the proposed approach is performed to observe the differences in final ranking of root risks and to highlight the arguments that strengthen the advantages of the proposed method over the other two.(c) 2023 Elsevier B.V. All rights reserved.