Criticality evaluation of petrochemical equipment based on fuzzy comprehensive evaluation and a BP neural network

Equipment criticality evaluation is an important base for maintenance decision-making to prevent accidents and to optimize maintenance management in Reliability Centered Maintenance (RCM), particularly in a new petrochemical plant. In this study, a new model using fuzzy comprehensive evaluation is developed. To do so, this study focuses on the description of fuzzy comprehensive evaluation. In the evaluation, the following are considered as the influential factors: production loss, safety effect, environment effect and maintenance costs. In addition, this study also introduces Failure Mode and Effect Analysis (FMEA). Moreover, evaluation criteria and membership function of the influence factor are established. Likewise, the algorithm combining fuzzy comprehensive evaluation with a three-layer BP neural network is studied. An application study in an ethylene plant is provided as an example to demonstrate the feasibility of this model. The results show that this model is reliable and applicable for criticality evaluation of petrochemical equipment in RCM. Finally, based on the criticality evaluation results, some maintenance advices for RCM decision-making are proposed.