Aircraft key part damage prediction method, system, equipment, medium and product
By generating sample dual-channel stress history and training a temporal convolutional network model, the problem of high time consumption in calculating aircraft damage values in existing technologies is solved, achieving efficient damage prediction and meeting the needs of engineering applications.
Patent Information
- Application Number
- CN202610292131.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-11
- Publication Date
- 2026-06-05
AI Technical Summary
Existing technologies consume a lot of time and computing power in calculating damage values for aircraft structures, making it difficult to meet the engineering application requirements of life tracking for high-frequency updates.
By randomly generating multiple sample dual-channel stress histories, and combining material performance parameters and multi-axis fatigue calculation methods, a deep learning model based on a temporal convolutional network is trained, which is directly mapped to a data-driven fast prediction function to achieve end-to-end prediction of damage values in critical parts of aircraft.
It significantly improves the computational efficiency of damage prediction for critical parts of aircraft, meets the needs of single-aircraft life tracking for high-frequency, low-latency damage assessment, and maintains high-precision damage value prediction capability.