Developing a bi-objective maintenance optimization model for process industries by prioritizing resilience and robustness using dynamic Bayesian networks

Abstract

In this paper, we developed a new model that combines resilience concept with robust maintenance resource allocation, and team assignment strategies to evaluate system performance after disruption. This model offers insights for proactive preparation before disruptive events and facilitates optimal decision-making in the aftermath of such disruptions. Our approach involves a non-linear programming model that operates at both strategic and operational decision levels. It aims to simultaneously minimize total maintenance costs while maximizing resilience by determining the allocation of backup resources to system components before a disruption occurs and suggesting emergency maintenance team assignments post-disruption, all while adhering to resilience constraints.We quantify resilience using a dynamic Bayesian Network method and Markov process, utilizing metrics based on absorption, adaptation, and restoration performance (reliability) curves. We propose a bi-objective optimization model and leverage the genetic algorithm NSGA-III to obtain Pareto-optimal solutions. To address the inherent uncertainty of various disruption scenarios, we generate a range of possible scenarios and employ robust optimization techniques to derive solutions that can withstand these uncertainties. To demonstrate the effectiveness of our proposed model, we conduct a case study involving a City Gate Station in agas industry.