Aircraft fault diagnosis method, model training method, device and computer equipment
By constructing an atmospheric parameter model and a traceless Kalman filtering model, extracting multi-dimensional new information and residual sequences, and calling a pre-trained aircraft fault diagnosis model, the accuracy and reliability problems of aircraft atmospheric data system fault diagnosis in the existing technology are solved, and timely and accurate diagnosis of aircraft faults is achieved.
Patent Information
- Application Number
- CN202410844381.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-27
- Publication Date
- 2025-03-18
- Estimated Expiration
- 2044-06-27
AI Technical Summary
The prior art is difficult to accurately diagnose the faults of the aircraft atmospheric data system in harsh flight environments, especially small-scale faults and fault diagnosis in uncertain flight conditions.
By obtaining the measurement information of the atmospheric data system and inertial navigation system in the aircraft system, an atmospheric parameter model is constructed, and a traceless Kalman filtering model is established based on this, multi-dimensional new information and residual sequences are extracted as input, and a pre-trained aircraft fault diagnosis model is called for diagnosis.
It realizes accurate diagnosis of the aircraft's atmospheric data system faults, improves the fault detection capability in harsh environments and uncertain states, and ensures the safe flight of the aircraft.