Abstract
Under the variable working condition, the fault signal of the rolling bearing contains rich characteristic information. In view of the problem that the traditional fault diagnosis method of the rolling bearing depends on the prior knowledge and expert experience too much and the low recognition rate of some faults with the single signal, one method of rolling bearing fault diagnosis based on information fusion under the variable working condition is proposed. Firstly, one test and multi-information acquisition system of the rolling bearing is built. Secondly, the metro traction motor bearing nu216 is selected as the research object, and to prefabricate the defects, the data of acoustic emission and vibration acceleration signals during the test of the bearing is acquired. Then, the original signal is processed and extracted by the wavelet packet decomposition, and the normalized feature information is fused by the convolution neural network. Finally, the two-dimensional convolution neural network model is established to diagnose the bearing fault of the metro traction motor under different conditions. The test results show that the intelligent fault diagnosis method of the subway traction motor bearing based on information fusion under variable working conditions can accurately identify the fault type of the bearing, while the load and speed change. When the neural network training set and the test set cover the same working conditions, the accuracy can reach 100%.
Highlights
Operating under the harsh working conditions of high temperature, alternating load, and long-time fatigue causes cracks, pitting corrosion, and other local damage or defects on the inner and outer ring raceways and rolling elements of the metro traction motor bearings, and it can cause abnormal noise and vibration of the traction motor
The convolution neural network is used to fuse the acoustic emission and vibration information characteristics during the bearing test of the metro traction motor under different working conditions, and the intelligent fault diagnosis method of the metro traction motor bearing based on deep learning and information fusion is studied under variable working conditions
According to the number of input layer elements, the convolution layer is 2 layers, the pooling layer is 2 layers, the full connection layer is 1 layer, and the output layer is using the “Softmax” classifier. e convolution kernel is set to 3 × 3, the sliding step size is set to 1, the learning rate is 0.001, and the activation function is “relu” activation function
Summary
Operating under the harsh working conditions of high temperature, alternating load, and long-time fatigue causes cracks, pitting corrosion, and other local damage or defects on the inner and outer ring raceways and rolling elements of the metro traction motor bearings, and it can cause abnormal noise and vibration of the traction motor. By learning the internal rules and representation levels of sample data, repeatedly nesting feature transformation, and automatically learning the internal characteristics of the data, deep learning can actively mine the representative diagnostic information hidden in massive original data and can directly establish the accurate mapping relationship between the running state and the original data It largely gets rid of the dependence on the experience of artificial feature design and engineering diagnosis [13]. Li Heng [16] used short-time Fourier transform, Zhang et al [17] used the multichannel sample construction method, and Chen et al [18] used the discrete wavelet transform and convolution neural network, respectively, to study rolling bearing fault based on deep learning All of these methods using the convolution neural network to intelligently diagnose the fault of the rolling bearing have achieved good results, but they are based on the test data collected by Case Western Reserve University. The convolution neural network is used to fuse the acoustic emission and vibration information characteristics during the bearing test of the metro traction motor under different working conditions, and the intelligent fault diagnosis method of the metro traction motor bearing based on deep learning and information fusion is studied under variable working conditions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
