Research on intelligent diagnostic techniques for rolling bearings based on unbalanced data sets

Abstract

In this paper, based on the combination of comprehensive sampling and one-dimensional convolutional neural network, a bearing fault intelligent diagnosis technique is proposed for the classification of rolling bearing vibration data. At first, the fault data set is expanded by ADASYN method. Then, the data is cleaned up by Tomek link under sampling technique, the risk of overfitting caused by overlap of different classes is reduced and the data of different categories is more apparent, and finally the normal data set and fault data set after comprehensive sampling are classified by one-dimensional convolutional neural network algorithm. Compared with random forests and support vector machines, the results show that the method has a high accuracy in identifying classifications and can effectively solve the classification problem of unbalanced bearing data.

Keywords

• unbalanced data set
• comprehensive sampling
• convolutional neural network
• rolling bearings
• fault diagnosis