An Aerospace Equipment Operation and Maintenance Scheduling Method Based on LLM and Solver

In this paper, an integrated management approach was proposed for aerospace equipment maintenance based on large language models (LLMs) and optimization solvers, aiming to improve the efficiency and convenience of maintenance decision support. A dataset tailored to maintenance scenarios in the aerospace domain was constructed, and the GLM4-9B model was fine-tuned using the LoRA method to accurately understand and invoke maintenance task instructions. Combining the OR-Tools optimization solver, a two-stage algorithm was designed to optimize maintenance resource allocation and vehicle routing. On this basis, a prototype system for integrated maintenance management based on LLMs and optimization solvers is implemented, validating the effectiveness of the proposed approach. The proposed method was demonstrated by experimental results to significantly improve the accuracy and efficiency of maintenance decision-making in the aerospace domain, offering new insights for aerospace equipment maintenance management.