Bearing Fault Diagnosis Using Convolution Neural Network and Support Vector Regression

Abstract

Rolling bearing is one of the most widely used parts in machinery. The vibration signals measured from a rolling bearing can reflect the conditions of the bearing, so the vibration signal is often used in the field of bearing fault diagnosis. A number of diagnostic techniques have been studied based on the vibration signals. Deep learning theory is usually used in image recognition or speech processing, and it has attracted more and more attentions in fault diagnosis. In this paper, a method based on deep learning and support vector regression is proposed. The convolutional neural network which is seldom used for one dimension signal is used for promoting feature extraction capability. Besides, the support vector regression (SVR) is an upgrading of the support vector machine which has great generalization ability and can be improved for classification by regression theory. The proposed method is achieved through a hybrid model which combines these two techniques. The presented method is used to classify the bearing fault patterns and obtains better results than that of the convolutional neural network and support vector regression machine separately.