Fault Diagnosis Based on Multi-layer Structure Wavelet Neural Networks in Attitude Heading Reference System

According to the structure feature of aircraft's attitude heading reference system and procedure of fault diagnosis, this paper sets up multi-layer neural network model structure for fault diagnosis of complex equipment, and applies the model to the fault diagnosis of attitude heading reference system in aircraft. The conclusion is that the method can effectively reduce the complexity of fault diagnosis for complex system, and imp rove diagnosis rate and efficiency of attitude heading reference system. At the same time, it also provides a new method and theory to diagnosis the non-linear system.