基于改进CNN的轴承声学故障诊断

doi:10.16180/j.cnki.issn1007-7820.2023.01.011

Abstract

Abstract:

In view of the difficulty to collect bearing vibration signals in complex machinery and the poor accuracy of traditional fault diagnosis methods under cross working speed conditions, a rolling bearing acoustic fault diagnosis method is proposed based on TEO-CNN. Teager energy operator of raw acoustic signals is taken as the input of TEO-CNN model, the CNN is employed to extract the abstract features from inputs, and the global average pooling layer and the fully connected layer are combined to recognize the bearing health status. TEO-CNN is verified on bearing acoustic experimental data sets, and cross working speed conditions are simulated by constructing different bearing acoustic data sets. Experimental results show that compared with traditional convolutional neural networks and machine learning models, the proposed TEO-CNN shows obvious superiority, and the prediction accuracy is always higher than 95% under cross working speed conditions.

Key words: convolutional neural network, Teager energy operator, acoustic-based fault diagnosis, rolling bearing, cross working speed conditions, global average pooling

CLC Number:

TP391.5

HUANG Yajing,LIAO Aihua,YU Miao,LI Xiaolong,HU Dingyu. An Improved CNN Method for Bearing Acoustic Fault Diagnosis[J].Electronic Science and Technology, 2023, 36(1): 75-80.

Figures/Tables 13

Figure 1.

Table 1.

Figure 2.

Figure 3.

Table 2.

Figure 4.

Figure 5.

Figure 6.

Table 3.

Figure 7.

Table 4.

Table 5.

Figure 8.

References 18

[1]	郑国刚, 戴光泽, 张敏男. 基于能量熵和EEMD结合的滚动轴承故障诊断方法[J]. 现代制造工程, 2021(5):139-145.
	Zheng Guogang, Dai Guangze, Zhang Minnan. Fault diagnosis method of rolling bearing based on energy entropy and EEMD[J]. Modern Manufacturing Engineering, 2021(5):139-145.
[2]	Liu R, Yang B, Zio E, et al. Artificial intelligence for fault diagnosis of rotating machinery: A review[J]. Mechanical Systems & Signal Processing, 2018, 10(8):33-47.
[3]	李卫鹏, 曹岩, 李丽娟. 正交小波变换k-中心点聚类算法在故障诊断中的应用[J]. 振动与冲击, 2021, 40(7):291-296.
	Li Weipeng, Cao Yan, Li Lijuan. Orthogonal wavelet transform KCA in fault diagnosis[J]. Journal of Vibration and Shock, 2021, 40(7):291-296.
[4]	蒋玲莉, 谭鸿创, 李学军, 等. 基于CEEMDAN排列熵与SVM的螺旋锥齿轮故障识别[J]. 振动.测试与诊断, 2021, 41(1):33-40.
	Jiang Lingli, Tan Hongchuang, Li Xuejun, et al. Fault diagnosis of spiral bevel gear based on CEEMDAN permutation entropy and SVM[J]. Journal of Vibration,Measurement & Diagnosis, 2021, 41(1):33-40.
[5]	牟竹青. 基于KPCA-LSSVM的单向阀故障诊断研究[J]. 电子科技, 2019, 32(3):10-14.
	Mou Zhuqing. Study on the fault diagnosis of check valve based on KPCA-LSSVM[J]. Electronic Science and Technology, 2019, 32(3):10-14.
[6]	徐欣怡, 徐永能, 任宇超. 基于小波神经网络的地铁轴承故障诊断方法[J]. 兵器装备工程学报, 2020, 41(12):177-181.
	Xu Xinyi, Xu Yongneng, Ren Yuchao. New wavelet neural network method for fault diagnosis of metro bearings[J]. Journal of Ordnance Equipment Engineering, 2020, 41(12):177-181.
[7]	Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 11(5):213-237.
[8]	Zhang W, Li C, Peng G, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2017, 10(4):439-453. doi: 10.1006/mssp.1996.0031
[9]	邓佳林, 邹益胜, 张笑璐, 等. 一种改进CNN在轴承故障诊断中的应用[J]. 现代制造工程, 2020(4):142-147.
	Deng Jialin, Zou Yisheng, Zhang Xiaolu, et al. Application of an improved CNN in fault diagnosis of bearings[J]. Modern Manufacturing Engineering, 2020(4):142-147.
[10]	闫书豪, 乔美英. 基于一维Wconv-BiLSTM的轴承故障诊断算法[J]. 电子科技, 2021, 34(4):75-82.
	Yan Shuhao, Qiao Meiying. Bearing fault diagnosis algorithm based on one-dimensional Wconv-BiLSTM[J]. Electronic Science and Technology, 2021, 34(4):75-82.
[11]	Yao J, Liu C, Song K, et al. Fault detection of complex planetary gearbox using acoustic signals[J]. Measurement, 2021, 178(4):1-14.
[12]	Yao J, Liu C, Song K, et al. Fault diagnosis of planetary gearbox based on acoustic signals[J]. Applied Acoustics, 2021, 18(1):1-11. doi: 10.1016/0003-682X(85)90002-7
[13]	Zhang D, Stewart E, Entezami M, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network[J]. Measurement, 2020, 15(6):1-9. doi: 10.1016/0263-2241(94)00031-2
[14]	王桥梅, 吴浩, 杨杰, 等. 基于Teager能量算子和1D-CNN的HVDC输电线路故障识别方法[J]. 智慧电力, 2021, 49(5):93-100.
	Wang Qiaomei, Wu Hao, Yang Jie, et al. Fault identification method of HVDC transmission line based on teager energy operator and 1D-CNN[J]. Smart Power, 2021, 49(5):93-100.
[15]	Rodríguez P H, Alonso J B, Ferrer M A, et al. Application of the Teager-Kaiser energy operator in bearing fault diagnosis[J]. Isa Transactions, 2013, 52(2):278-284. doi: 10.1016/j.isatra.2012.12.006 pmid: 23352553
[16]	Han T, Liu Q, Zhang L, et al. Fault feature extraction of low speed roller bearing based on Teager energy operator and CEEMD[J]. Measurement, 2019, 13(8):400-408.
[17]	谢锋云, 符羽, 王二化, 等. 基于多特征提取和LSSVM的轴承故障诊断[J]. 机床与液压, 2020, 48(17):188-190.
	Xie Fengyun, Fu Yu, Wang Erhua, et al. Bearing fault diagnosis based on multi-feature extraction and LSSVM[J]. Machine Tool & Hydraulics, 2020, 48(17):188-190.
[18]	Yang Z, Wang C, Oja E. Multiplicative updates for t-SNE[C]. Kittila: Proceeding of IEEE International Workshop on Machine Learning For Signal Processing, 2010.

层类型	核尺寸@个数	步长
卷积层1	64×1@16	2
池化层1	2×1	2
卷积层2	8×1@32	2
池化层2	2×1	2
卷积层3	3×1@64	2
池化层3	2×1	2
全连接层	(64,6)	-

轴承类型	转速	7 Hz		8 Hz
轴承类型	标签	训练集 A	测试集 A	训练集 B	测试集 B
正常	0	600	200	600	200
内圈	1	600	200	600	200
外圈	2	600	200	600	200
滚珠	3	600	200	600	200
内圈+滚珠	4	600	200	600	200
外圈+滚珠	5	600	200	600	200

模型	数据集A	数据集B	平均值
TEO-CNN	100.00%	99.96%	99.98%
CNN	98.77%	99.14%	98.96%
SVM	97.78%	96.93%	97.36%
MLP	94.29%	96.42%	95.36%

数据集	训练集	测试集
A→B	训练集A	测试集B
B→A	训练集B	测试集A
A & B	训练集A+B	测试集A+B

	A→B	B→A	A & B
TEO-CNN	96.82±0.10	97.59±0.25	99.48±0.36
CNN	91.16±0.93	93.61±0.89	97.29±0.51
SVM	87.56±1.65	87.07±0.78	95.04±0.64
MLP	57.20±2.80	46.30±4.12	91.03±1.83

An Improved CNN Method for Bearing Acoustic Fault Diagnosis

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 18

Related Articles 15

Metrics

Comments

Recommended 10

[1]	ZUO Bin,LI Feifei. An Effective Segmentation Method for COVID-19 CT Image Based on Attention Mechanism and Inf-Net [J]. Electronic Science and Technology, 2023, 36(2): 22-28.
[2]	DENG Yuan,SHI Yiping,JIANG Yueying,ZHU Yamei,LIU Jin. Infant Expression Recognition Algorithm Based on MobileNetV2 and LBP Feature Fusion [J]. Electronic Science and Technology, 2022, 35(8): 47-52.
[3]	SHEN Ningjing,YUAN Jian. Crowd Counting Algorithm Based on Residual Dense Connection and Attention Fusion [J]. Electronic Science and Technology, 2022, 35(6): 6-12.
[4]	Chaowei LIN,Feifei LI,Qiu CHEN. Globaland Local Scene Representation Method Based on Deep Convolutional Features [J]. Electronic Science and Technology, 2022, 35(4): 20-27.
[5]	Meiyi QI,Aihua LIAO. Design of Reliability Evaluation System of Traction Motor Rolling Bearing Based on MATLAB App Designer [J]. Electronic Science and Technology, 2022, 35(3): 79-86.
[6]	LI Hui,WANG Yicheng. CNNCIFG-Attention Model for Text Sentiment Classifcation [J]. Electronic Science and Technology, 2022, 35(2): 46-51.
[7]	DENG Lei,SUN Peiyang. Research on Network Public Opinion Monitoring System Based on Deep Learning [J]. Electronic Science and Technology, 2022, 35(12): 97-102.
[8]	ZHAN Yinwei,ZHU Baiwan,YANG Zhuo. Research and Application of Vehicle Face Recognition Algorithm [J]. Electronic Science and Technology, 2021, 34(8): 1-7.
[9]	LIAO Luming,ZHANG Wei. Batch Mixed Training Traffic Sign Recognition Based on Improved VGG16 Network [J]. Electronic Science and Technology, 2021, 34(8): 8-13.
[10]	GU Wei,LI Feifei,CHEN Qiu. Pedestrian Detection Algorithm Based on Multiple Feature Fusion [J]. Electronic Science and Technology, 2021, 34(5): 29-34.
[11]	XUE Yongjie,JU Zhiyong. Fish Recognition Algorithm Based on Improved AlexNet [J]. Electronic Science and Technology, 2021, 34(4): 12-17.
[12]	ZHANG Can,CHEN Wei,YIN Zhong. Semantic Segmentation of Cervical Cell Image Based on Weak Supervision [J]. Electronic Science and Technology, 2021, 34(12): 68-74.
[13]	ZHANG Ying,LIU Zilong,WAN Wei. UAV Vehicle Target Detection Based on Faster R-CNN [J]. Electronic Science and Technology, 2021, 34(11): 11-20.
[14]	LI Cheng,LIU Hao,JIANG Xifeng,WU Junfa,HAN Wengang,GAO Jianguo. Intelligent Diagnosis Algorithm of Generator Stator and Rotor Based on VGG Network [J]. Electronic Science and Technology, 2021, 34(11): 62-66.
[15]	ZHANG Xiang,SHI Zhicai,CHEN Liang. Expression Recognition Method Based on Cascade Network Optimized by SWA [J]. Electronic Science and Technology, 2020, 33(9): 16-20.