Maintenance decision methodology of petrochemical plant based on fuzzy curvelet neural network

The maintenance decision of petrochemical plant is a main factor to ensure the reliability and safety of petrochemical plant, in order to make the optimal maintenance decision of petrochemical plant, and the fuzzy curvelet neural network is constructed to solve this problem. The maintenance model of petrochemical plant is established through considering economy and reliability, and the failure rate and maintenance cost models of petrochemical plant are deduced. The architectural framework of fuzzy curvelet neural network is designed, which concludes five layers, and the optimal algorithm procedure is designed based on improved particle swarm algorithm. The simulation analysis of predicting maintenance cost and failure rate for 1 million tons/year gasoline hydrodesulphurization unit is carried out based on three different decision methods, the new method has best precision by comparing simulation results with actual data, and the maintenance cost and failure rate of the unit from 2017 to 2022 are predicted. In addition, the best maintenance plans are confirmed through predicting simulation bases on the proposed method. The proposed maintenance decision model offers scientific guidance as a basis for action by overhaul decision makers of a petrochemical plant. (C) 2018 Elsevier B.V. All rights reserved.