Avionic Fault Diagnosis Expert System Based on Flight Data and BIT Information

According to the characteristics of onboard equipments fault diagnosis and the development tendency of this field, diagnostic technique and diagnostic method based on CBR are studied. A fault diagnosis method for a certain type of aircraft is put forward. This method adopts CBR strategy based on BIT message, flight parameter, and other fault symptoms. A fault diagnosis expert system is designed. The Rough Set theory is used in this system to process the fault symptoms to reduce the number and dimension of the symptoms and to calculate the weightness of each symptom. The Nearest Neighbor method is set as a global matching strategy which achieves the most matched results accurately. At last, the performance of this system is verified.