Research on coherent fault diagnosis of aircraft based on probability causal network

Nowadays, the Built-in test (BIT) technique is adopted widely in aircraft fault diagnosis and maintenance. However, because of the complicated structure, mass data transmission, and especially propagations of coherent faults in aircraft, it is difficult to localize faults and to guarantee the accuracy and efficiency of BIT fault diagnosis. To reduce the high BIT false alarm rate (FAR), the coherent fault diagnosis model of aircraft based on probability causal network is built, and the two-stage diagnosis algorithm is proposed based on ICGS reasoning and most likelihood function evaluating, and subsequently, the corresponding coherent fault diagnosis expert system is designed. The results of a coherent fault diagnosis example show that the proposed method has higher validity and engineering practicability.