Research on Gearbox Fault Diagnosis Based on DCNN and XGBoost

Abstract

In order to solve the problem of complex fault diagnosis of gearbox, the DCNN (Deep Convolution Neural Network) was combined with the XGBoost (eXtreme Gradient Boosting) algorithm to establish the fault diagnosis model. Firstly, the DCNN Model was used to adaptively extract the feature matrix of the original vibration acceleration signal. Secondly, the XGBoost model was trained by the feature matrix, so the gearbox fault diagnosis model of DCNN-XGBoost was obtained. Finally, the visualization effect of the feature matrix obtained by DCNN is better than that of the artificial extraction feature matrix; and the diagnostic accuracy of DCNN-XGBoost model is better than DCNN model.