Author(s)

Jianguang Yuan¹, Hongmin Liu², Yinghua Wang^1,2,*

Affiliation(s)

¹ College of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, Shandong, China;

² TBEA Hengyang Transformer Co., Ltd, Hengyang 421007, Hunan, China.

Corresponding Author

Yinghua Wang

ABSTRACT

Rolling bearings are commonly used parts in rotating machinery. Due to their harsh working environment, they are prone to failure. Therefore, a fault diagnosis method for rolling bearings based on parallel 1DCNN (one-dimensional convolutional neural network) is proposed. First, the vibration signal of the rolling bearing was processed and divided into training set and test set; then, a parallel 1DCNN model composed of two channels was constructed, which can obtain the time domain information and frequency domain information of the vibration signal respectively. A relatively small convolution kernel is used when extracting time domain information, and a relatively large convolution kernel is used when extracting frequency domain information, and the traditional fully connected layer is replaced by a global maximum pooling layer; finally, the trained The parallel 1DCNN model processed the rolling bearing test set data of Case Western Reserve University; at the same time, in order to verify the fault diagnosis effect of the parallel 1DCNN model, the model was compared with the traditional CNN model. The research results show that the fault diagnosis accuracy of the parallel 1DCNN model is higher than 0.996. Compared with the traditional single-channel CNN model, the parallel 1DCNN model can make full use of the extracted time domain and frequency domain feature information, and has better fault diagnosis ability.

KEYWORDS

Rolling bearing; Fault diagnosis; Convolutional neural network; 1DCNN; Deep learning; Feature extraction.

CITE THIS PAPER

Jianguang Yuan, Hongmin Liu, Yinghua Wang. Research on rolling bearing fault diagnosis based on parallel 1DCNN. World Journal of Engineering Research. 2023, 1(1): 1-7.

REFERENCES

[1] Song Yuyu, Liu Zhaoliang. Research on Rolling Bearing Fault Diagnosis Based on ICEEMD-EFICA Combined Noise Reduction. Mechanical and Electrical Engineering, 2021, 38 (4): 494-497, 520.

[2] Zhu Guanlin, Wang Zhaoqiang, Wang Yifan. Research on hydraulic pump fault diagnosis based on neural network and evidence fusion. Mechanical and Electrical Engineering, 2020, 37(12): 1498- 1503.

[3] Qu Jianling, Yu Lu, Yuan Tao. Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network. Journal of Instrumentation, 2018, 39 (7): 134-143.

[4] Han Tao, Yuan Jianhu, Tang Jian. Intelligent composite fault diagnosis method for rolling bearings based on MWT and CNN. Mechanical Transmission, 2016, 40 (12): 139-143.

[5] Wu Chunzhi, Jiang Pengcheng, Feng Fuzhou. Gearbox fault diagnosis based on one-dimensional convolutional neural network. Vibration and Shock, 2018, 37(22): 51-56.

[6] Zhang Xiangyang, Chen Guo, Hao Tengfei. Convolutional neural network diagnosis method for rolling bearing faults based on casing signals. Journal of Aerodynamics, 2019, 34 (12): 2729-2737.

[7] Wang Hailong, Xia Xiaoyun, Sun Weitang. Rolling bearing fault diagnosis based on EMD and convolutional neural network. Combined Machine Tool and Automatic Processing Technology, 2019 (10): 46-48, 52.

[8] Dong Shaojiang, Yang Shuting, Wu Wenliang. Bearing fault diagnosis method based on anti-noise multi-core convolutional neural network. Journal of Beijing University of Chemical Technology: Natural Science Edition, 2020, 47(6): 100-106.

[9] Liu Hongjun, Wei Xuyang. Research on rolling bearing fault diagnosis based on GADF and convolutional neural network. Mechanical and Electrical Engineering, 2021, 38(5): 587-591.

[10] Zhao R, Yan RQ, Chen ZH. Deep learning and its applications to machine health monitoring. Mechani- cal Systems and Signal Processing, 2019, 115: 213-237.