Self-Adaptive Risk-Based Inspection Planning in Petrochemical industry by evolutionary algorithms

Abstract

This research proposes a multi-objective mathematical model for Self-Adaptive Risk-Based Inspection Planning (SARBIP). Risk management is essential to organizations to ensure that a proper maintenance strategy is in place. An inspection plan is required to improve the overall safety and achieve optimal configurations for the investment, repair, and maintenance, in order to minimize the total expenses. To this end, a SARBIP model is proposed to obtain optimal solutions. The proposed model serves a dual purpose by reducing both the expenses and risk level. The proposed algorithm, which is used as the model's solution, is validated by being applied to a real case study in the Iranian petrochemical industry. The model is executed through two algorithms, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and the Multi-Objective Particle Swarm Optimization (MOPSO). The outcomes indicate that MOPSO outperforms other algorithms in large-scale problems.