Aircraft Engine Maintenance Based on Reinforcement Learning

Abstract

In recent years, with the rapid development of China's civil aviation industry, the maintenance of aircraft engines has grown rapidly in terms of both the number of repairs and the repair capacity. The structure of aero engine is complex, and the technical requirements for maintenance are high. During the operation of the aircraft, the engine equipment will decay due to fatigue, wear, aging and other reasons. Running equipment in a decay state often causes increased costs, increased failure rates, and huge safety risks. Proper maintenance can prevent equipment from operating in poor conditions, but excessive maintenance can increase equipment downtime and maintenance costs. According to the development trend of the state and possible failure modes, adopting corresponding maintenance strategies, preparing maintenance in advance, and adjusting the flight plan reasonably, this is of great significance for reducing equipment maintenance costs, improving operating efficiency and system safety, and improving the revenue of aviation companies.