Optimisation of Maintenance, Repair and Operations System Using Computational Intelligence Technique
Abstract
Maintenance, Repair and Operations (MRO) activities play a critical role in determining the reliability, availability, safety, and cost effectiveness of industrial assets. In many industrial environments, traditional maintenance strategies are designed to optimize a single performance indicator, typically maintenance cost or failure frequency. Such approaches often lead to suboptimal outcomes when conflicting objectives such as downtime reduction, system availability, reliability improvement, and environmental impact are considered simultaneously. This study presents a multi-objective optimization framework for MRO systems using computational intelligence techniques, validated through an industrial maintenance case study. The proposed framework integrates key maintenance performance indicators including Mean Time Between Failures (MTBF), Mean Time To Repair (MTTR), system availability, maintenance cost, and environmental impact into a unified decision-support model. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to generate Pareto-optimal maintenance strategies that balance competing objectives. Results obtained from the case study demonstrate significant improvements in system availability, reduction in downtime, and lower lifecycle maintenance costs compared to the existing maintenance policy. The findings confirm that computational intelligence-based multi-objective optimization provides a robust, flexible, and practical approach for solving complex MRO decision problems in industrial systems.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ayanniran Precious, Okachi Ikegwuru Ibezimakor, Uchendu Imereoma Frank (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.