Research on Fault Diagnosis Method of Gearbox Based on SA and BP-AdaBoost

In order to solve the problems of difficult selection of state feature parameters and poor accuracy of single BP Neural Network in gearbox fault diagnosis, a gearbox fault diagnosis method based on SA and BP-AdaBoost is proposed. Taking the typical fault of a gearbox as the research object, the vibration signal of the typical working state of the gearbox is collected through the preset fault experiment. The time domain statistical parameters with high sensitivity is selected as the feature vectors by the Sensitivity Analysis method. Then these state feature vectors are input into BP-AdaBoost model for training and testing, and their results are compared with those of BPNN model. The results show that the proposed method can quickly and effectively diagnose the fault of gearboxe, and is better than BPNN model.