Neural network-based aero-engine sensor fault diagnosis method and system

The invention discloses an aero-engine sensor fault diagnosis method and system based on a neural network, and the method comprises the steps: firstly obtaining a sample data set of an aero-engine sensor, and extracting feature parameters in the sample data set to obtain a feature set; determining an optimal characteristic parameter with the highest matching degree, and updating a balance parameter and an adaptive parameter in the HPO algorithm according to the optimal characteristic parameter and the corresponding matching degree; updating the feature set according to the updated balance parameter and adaptive parameter and the average value of all feature parameters in the feature set; determining the matching degree of each feature parameter in the updated feature set, and updating the optimal feature parameter according to the matching degree of each feature parameter; and predicting the fault type of the aero-engine sensor according to the optimal characteristic parameters. According to the method, featu