Diagnostic parameters selection of aero-engine based on BP network

Selecting diagnostic parameters of aero-engine performance is an essential approach to enhance the accuracy and reliability of aero-engine fault recognition. In view of the strong sensitivity of diagnostic parameters to the system state, an algorithm based on BP network was put forward and used for fault recognition of one aero-engine. The result shows that the diagnostic parameters selected by the algorithm are the key factors of aero-engine failure, whereby the algorithm ensures high precision of fault diagnosis. At the same time, the anti-interference ability of the algorithm enhances the validity of fault recognition. The algorithm can be also used for fault classification, fault diagnosis and performance monitoring aero-engine.