Fault Diagnosis for Rotating Machinery Gearbox based on 1DCNN-RF

Abstract

In this paper, a fault diagnosis method combining one-dimensional convolutional neural network (1DCNN) and random forest (RF), which is called 1DCNN-RF, is proposed for rotating machinery gearbox. This method uses 1DCNN to extract features from the collected multiple sensor signals, and then uses RF algorithm for classification. Compared to the existing approaches, this algorithm can improve the accuracy of fault diagnosis for rotating machinery gearbox. Finally, experiments are conducted on the Wind Turbine Drivetrain Diagnostic Simulator (WTDDS) to show the effectiveness of the proposed scheme.