Multi-Criteria Optimization of Production Processes of Mining Companies

Equipment selection is a critical decision in mining operations, directly influencing production efficiency, maintenance requirements, and operational costs. However, this decision is complicated by significant uncertainty surrounding equipment performance and remaining service life. This paper presents a hybrid decision support framework that integrates Fuzzy Logic, Pareto Optimality, and a Genetic Algorithm (GA) to address the challenge of roadheader selection under such uncertainty. The proposed Fuzzy–Pareto–GA approach applies fuzzy logic to model the inherent uncertainty in performance data; employs Pareto optimization to identify optimal trade-offs between multiple, often conflicting criteria; and utilizes a genetic algorithm to efficiently navigate the solution space. The framework is validated using real-world data from an operating mining company, considering three key criteria: operating time, remaining service life, and the remaining service life ratio. The results demonstrate that the fuzzy–Pareto approach effectively identifies a set of non-dominated solutions, and the robustness of these rankings is confirmed through a comprehensive sensitivity analysis. The proposed framework offers mining engineers a transparent and uncertainty-aware tool for equipment selection, a decision that serves as a critical foundation for effective production process optimization.