Rolling-Element Bearing Fault Data Automatic Clustering Based on Wavelet and Deep Neural Network

Yanli Yang,Peiying Fu

doi:10.1155/2018/3047830

Abstract

A method based on wavelet and deep neural network for rolling-element bearing fault data automatic clustering is proposed. The method can achieve intelligent signal classification without human knowledge. The time-domain vibration signals are decomposed by wavelet packet transform (WPT) to obtain eigenvectors that characterize fault types. By using the eigenvectors, a dataset in which samples are labeled randomly is configured. The dataset is roughly classified by the distance-based clustering method. A fine classification process based on deep neural network is followed to achieve accurate classification. The entire process is automatically completed, which can effectively overcome the shortcomings such as low work efficiency, high implementation cost, and large classification error caused by individual participation. The proposed method is tested with the bearing data provided by the Case Western Reserve University (CWRU) Bearing Data Center. The testing results show that the proposed method has good performance in automatic clustering of rolling-element bearings fault data.

Highlights

Rolling-element bearings are widely used in industry
Testing and Analysis e proposed method is tested by using the Case Western Reserve University (CWRU) bearing data with faults in 0.021 inch. ese data include 12k driveend, 48k drive-end, and 12k fan-end bearing data. e designed deep neural network (DNN) has six layers. e number of decomposition layers of wavelet packet transform (WPT) is 8. us, the input layer of the DNN has 256 arti cial neurons. e hidden layer of the DNN is set as 200130-80-50. e number of output-layer neurons is determined by the types of sample labels, which can be adjusted dynamically. e weights of the DNN are initialized randomly. e learning rate and the batch size are set to 1
For the 12k fan-end 0.021-inch bearing data, the 36 records are given a unique label that is a random number between 1 and 36. ese records are divided into 29 and 4 categories through the rough and the fine classifications, respectively. e classification results are shown in Figure 14, and the WPT energy vectors of each class are shown in Figure 15 which displays a clear difference between the WPT energy vectors of samples for different classes

Summary

Introduction

Rolling-element bearings are widely used in industry. Such bearings play a pivotal role in the rotating machine because they can reduce friction between moving parts and allow the machine to operate efficiently. Time-domain vibration signals are decomposed by the WPT to build a training dataset in which the samples are labeled randomly. In the ne classi cation process, the raw data are divided into small sections with lengths of 16,384, 8192, 4096, and 2048 to test the trained DNN. 12k drive-end bearing data, all the testing results are accurate except for the subsignals of length 2048 with 19 misclassified samples. To further prove the validity of the classification, the first three PCs of the features extracted the DNN are

Second0PC–1 –2

Findings

Conclusion