飞行器热管理模型构建方法、系统、计算机设备及介质
By using a modified zero-dimensional equivalent thermal path model and deep reinforcement learning, the temperature control problem of the aircraft thermal management system was solved, achieving precise real-time optimization and efficient energy management, thereby improving the overall performance and safety of the aircraft.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2025-12-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing aircraft thermal management systems cannot precisely control the temperature of power system components, leading to inefficiency and safety hazards. Traditional optimization methods are difficult to handle high-dimensional, nonlinear, and strongly coupled multi-objective optimization problems, and existing models cannot optimize online in real time.
A modified zero-dimensional equivalent thermal path model is constructed and combined with a deep reinforcement learning model. Through high-fidelity three-dimensional thermodynamic calculations and wind tunnel verification, an accurate thermal management strategy is generated. Thermal nodes and heat transfer paths are integrated for real-time online optimization.
It achieves precise temperature control of the aircraft's thermal management system, improves the overall energy utilization and safety of the aircraft, reduces hydrogen consumption by 7%-15%, and reduces component performance degradation and safety risks.
Smart Images
Figure CN121744514B_ABST