Fault Diagnosis Based on Fault Tree and Bayesian Network with Grey Optimization

Remote-controlled engine ignition of unmanned aerial vehicle (UAV) is the key node for its successful flight mission. The effective fault diagnosis and prevention of remote-controlled engine is the guarantee of its safe and reliable operation. This paper proposes a fault diagnosis method based on the fusion of fault tree (FT) and Bayesian network (BN). Further, a grey analysis model is employed to mine the in-depth information of the FT model, so as to find the key factors affecting the ignition failure of the remote-controlled engine, and provide support for maintenance and product design. Finally, the correctness and validity of the proposed model are verified by using a the typical fault mode of the remote-controlled engine.