Performance and predict the ball bearing faults using wavelet packet decomposition and ANFIS

Abstract

Element bearings are widespread significant parts of rotary machinery in industries and their condition monitoring through fault detection and isolation methods are of superior interests to engineers. Condition monitoring could assist in attaining effective system maintenance and the automation processes. Nonetheless, despite the availability of diverse bearing fault detection methods, there is paucity of literature concerning the theoretical modelling of the bearing faults using mathematical representations. The principal goal of this communication is to build up an approach to predict ball bearing fault, including ball fault, outer race fault and inner race fault. The proposed method uses the vibration data collected from the rotating ball bearing and predicts the type of fault. The proposed method is based on wavelet decomposition method, PCA, ANFIS and SVM. The vibration data is decomposed into 3rd level wavelet components using wavelet packet decomposition; each wavelet component has been divided into several energy segments, these 3rd level wavelet components are reduced to lower level components using Principal Component Analysis (PCA). ANFIS algorithm is trained using the reduced feature set as input and the type of fault as output. The trained ANFIS algorithm is validated using another set of data. Support Vector Machine (SVM) has been used instead of ANFIS algorithm, the SVM based method gives more accurate prediction compared to that of ANFIS. The proposed method has been validated using the real-time data collected from the ball bearing setup. The validation results show that the proposed method exactly predicts the type of ball bearing fault. The real-time data validation results confirm the accuracy of the fault prediction method.

Keywords: Principal component analysis, support vector machine; ANFIS; bearing