Fault Diagnosis of Rotating Machinery Gear Based on Random Forest Algorithm

Aiming at the problems in conventional fault diagnosis of rotating machinery such as limited accuracy using a single classifier, a fault diagnosis method based on random forest algorithm composed of multiple classifiers is proposed in this chapter for rotating machinery gear fault diagnosis. This method improves the prediction accuracy through the ensemble learning of basis classifiers and greatly reduces the prediction time of the model. In this chapter, the wind turbine drivetrain diagnostic simulator is adopted as the experiment platform for the experimental verification of fault diagnosis with multiple working conditions and multiple faults.