Bio-inspired optimisation: methods and potential applications in maintenance management

Numerous studies have investigated bio-inspired optimisation methods for solving computationally intensive decision-making problems. However, implementing such methods in maintenance management has not been fully explored. This work identifies more opportunities and further examines the potential of these advanced optimisation approaches in this important area. We classify bio-inspired optimisation methods into three primary categories according to their mechanisms for generating candidate solutions. Given the predominance of swarm intelligence–based approaches in the literature, this review focuses on the ten most widely adopted algorithms within this category. Their computational frameworks are systematically described, and information regarding available software implementations is provided. Our particular emphasis is placed on the technical characteristics, advantages, limitations, and practical applications of these algorithms. It is hoped that our comparative performance analysis will help practitioners and researchers in maintenance management effectively apply these optimisation techniques in best practices and future research.