Multi Classification of Rolling Bearing Conditions based on Random Forest Classifier Model

In rotating machines, roller bearings have always been an important mechanical component and are prone for frequent inner race or outer race damages. Therefore, accurate and automatic classification of bearing conditions becomes significant for effective maintenance of machines.Traditionally, vibration features from raw data are extracted, faults are diagnosed and then classification is made. However, capture of dynamic information in vibration data during different operating conditions using traditional methods has been a serious challenge which leads to necessity of intelligent ingestion and processing of vibration data for classification of bearing conditions. The intelligent fault classification of rolling bearing faults based on Random Forest is proposed in this paper. The proposed model correctly classifies the different types of faults at different running conditions in real operation conditions, and the results are compared with existing techniques. The performance of the model is evaluated with various performance metrics such as Precision, Recall, F1-score and Accuracy. Better results are obtained from the proposed Random Forest model than from the existing work.