Optimization of the dependability of a hammer mill under budgetary constraints using a hybrid approach based on evolutionary algorithms and stochastic methods

Abstract

This article addresses the optimization of maintenance strategies for a hammer mill under budgetary constraints, using a hybrid approach that combines genetic algorithms with Monte Carlo simulation to account for system degradation and uncertainty. The goal is to maximize overall dependability—encompassing availability, maintainability, safety, and system reliability—while minimizing maintenance costs. A composite performance index is formulated using weighted indicators to support multi-criteria decision-making, and several candidate solutions are compared using the VIKOR method. The proposed simulation-based framework is applied to a real industrial case using field data over 24 months, demonstrating the method’s ability to generate robust, cost-effective strategies that outperform conventional optimization techniques. The approach ensures practical feasibility for offline planning and provides a reproducible and adaptable tool for optimizing complex industrial maintenance systems.