Enhanced Short-Term Scheduling of Underground Mining Activities Using Tabu Search: A Comparative Analysis

Abstract

The planning of preparation and development activities in underground mining is essential to ensure efficiency and operational continuity. However, short-term scheduling of these tasks has received limited attention in literature. This study proposes a Cooperative Multi-start Tabu Search with Path-Relinking (CMTS-PR), which coordinates multiple tabu trajectories and intensifies them through path relinking to optimize the short-term scheduling of multiple underground heading works within a one-shift horizon. The problem is modeled as a flexible job-shop scheduling problem with unrelated parallel equipment and sequence dependent setup times. CMTS-PR is evaluated against a memetic algorithm, a Non-dominated Sorting Genetic Algorithm II, a single-trajectory Tabu Search (TS), a Constraint Programming (CP) model, and manual scheduling by an expert planner, across two panel caving case studies in Chile. The results show that CP yields mathematically optimal solutions but becomes computationally demanding, while manual scheduling ensures feasibility but underutilizes resources. In contrast, CMTS-PR produces operationally viable schedules. In case study 1, CMTS-PR matched CP on equivalent fronts within 60 seconds, even under 10-60 minute transfer time variability. In case study 2, CMTS-PR increased equivalent fronts by 120% compared to manual planning and by 2.94% relative to CP, with lower runtime. Overall, CMTS-PR proves to be effective and computationally efficient, representing one of the first applications of a cooperative TS and path-relinking scheme to underground short-term scheduling, and providing a practical tool for daily mine operations.