基于MPGCN-Resnet的滚动轴承故障诊断研究

doi:10.3969/j.issn.1000-1158.2024.12.12

Abstract
Figure/Table
References (22)
Related Citation (15)

Download: PDF (870 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Rolling bearings are installed in various machine tools and other production machinery,and are prone to faults and failures,requiring continuous monitoring to ensure their safe and reliable operation.Therefore,a multiple parallel graphs convolutional neural residual networks (MPGCN-Resnet) is designed to complete the fault diagnosis of rolling bearings.MPGCN-Resnet consists of four parts in total.Among them,the time-frequency graph acquisition part based on cmor wavelet can complete refined processing of reconstruction and disassembly in various fault vibration signals.The feature acquisition part based on a multi-parallel network can improve generalization and accelerate convergence.The feature learning part under the residual structure graph neural network can utilize the residual structure to complete feature learning and can realize the in-depth exploration of fault characteristics of rolling bearings.The GAP-Softmax fault classification part can complete the effective diagnosis of rolling bearing faults.Comparative and analytical experiments are conducted on the accuracy and loss values of MPGCN-Resnet,IHDSVM-Alexnet and MSATM method under varying operating conditions and noise levels using the CWRU bearing dataset.The results show that the average fault diagnosis accuracy of MPGCN-Resnet for rolling bearings can reach 96.4%,which is higher than 91% in a -6 dB noise environment and greater than 90% when the load suddenly changes by 3×0.75kW.MPGCN-Resnet has higher fault diagnosis accuracy for rolling bearings in various variable working conditions and variable noise environments than the other two methods,and can alleviate the problems of increased parameters and excessive calculation.

Key words： rolling bearing fault diagnosis graph convolutional neural network Cmor wavelet excessive calculation

Received: 11 March 2024 Published: 18 December 2024

PACS:

TB936

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	YAN Shengli
	FU Hui
	LI Hao

Cite this article:

YAN Shengli,FU Hui,LI Hao. Research on Fault Diagnosis of Rolling Bearing Based on MPGCN-Resnet[J]. Acta Metrologica Sinica, 2024, 45(12): 1832-1840.

URL:

http://jlxb.china-csm.org:81/Jwk_jlxb/EN/10.3969/j.issn.1000-1158.2024.12.12 OR http://jlxb.china-csm.org:81/Jwk_jlxb/EN/Y2024/V45/I12/1832

[1]	邢婷婷, 关阳, 孙登云, 等. 基于FSDPC＿Otsu算法的滚动轴承故障研究 [J]. 计量学报, 2021, 42(11): 1466-1471.
[2]	张煜莹, 陆艺, 赵静. 基于增量学习的数控机床故障诊断系统 [J]. 计量学报, 2022, 43(11): 1456-1463.
[3]	阎瑞雪, 夏杰, 张荣, 等. 某轴承生产企业噪声作业工人对噪声危害和防护知识认知情况 [J]. 中国职业医学, 2019, 46(4): 497-500.
[7]	赖荣燊, 闫高强. 基于卷积神经网络的滚动轴承故障诊断研究综述 [J]. 机电工程, 2024, 41(2): 194-204.
[12]	杜飞, 杨云, 胡媛媛, 等. 一种简单的共享式多层梯度补给方法 [J]. 软件学报, 2020, 31(7): 2157-2168.
	DU F, YANG Y, HU Y Y, et al. Easy Way for Multilayer Gradient Supplies [J]. Journal of Software, 2020, 31(7): 2157-2168.
[4]	CHEN RX, HUANG Y, XU XY, et al. Rolling Bearing Fault Feature Extraction Method Using Adaptive Maximum Cyclostationarity Blind Deconvolution [J]. IEEE Sensors Journal, 2023, 23(15): 17761-17770.
[5]	KIM Y, KIM Y K. Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis [J]. Sensors, 2023, 23(23): 9311.
[6]	李天昊, 李志星, 王衍学. 基于小样本下改进ChaosNet的轴承故障诊断 [J]. 组合机床与自动化加工技术, 2024(2): 182-185, 192.
[8]	SHARMA K, GOYAL D, KANDA R. Intelligent Fault Diagnosis of Bearings based on Convolutional Neural Network using Infrared Thermography [J]. Proceedings of The Institution of Mechanical Engineers Part J-Journal of Engineering Tribology, 2022, 236(12): 2439-2446.
[10]	LI P D. A Multi-scale Attention-Based Transfer Model for Cross-bearing Fault Diagnosis [J]. International Journal of Computational Intelligence Systems, 2024, 17(1): 42.
[13]	LIU X Y, YANG S H, JI J W, et al. Improvement of Underwater Laser Ranging Accuracy Based on Wavelet Time-Frequency Analysis [J]. IEEE Photonics Journal, 2022, 14(6): 7856105.
[15]	LI Q, LI H, HU W Y, et al. Transparent Operator Network: A Fully Interpretable Network Incorporating Learnable Wavelet Operator for Intelligent Fault Diagnosis [J]. IEEE Transactions on Industrial Informatics, 2024, 20(6): 8628-8638.
[17]	肖斌, 郭经伟, 张兴鹏, 等. 基于融合池化和注意力增强的细粒度视觉分类网络 [J]. 模式识别与人工智能, 2023, 36(7): 661-670.
[18]	赵彦涛, 何永强, 贾利颖, 等. 基于时间序列单维卷积神经网络的水泥熟料游离钙软测量方法 [J]. 计量学报, 2020, 41(9): 1152-1162.
[20]	刘桂雄, 黄坚. 基于标签预留Softmax算法的机器视觉检测鉴别语义分割迁移学习技术 [J]. 光学精密工程, 2022, 30(1): 117-125.
[21]	朱清波, 石程, 李磊. 基于ADAM主动衰减退火算法的钢材缺陷检测 [J]. 组合机床与自动化加工技术, 2023 (1): 92-95, 100.
	YAN R X, XIA J, ZHANG R, et al. Analysis on The Awareness of Noise Hazard and Protection of Workers in an Axis-Bearing Manufacturing Enterprise [J]. China Occupational Medicine, 2019, 46(4): 497-500.
[11]	HANIF M S, BILAL M. Competitive Residual Neural Network for Image Classification [J]. ICT Express, 2020, 6(1): 28-37.
	ZHAO Y T, HE Y Q, JIA L Y, et al. Soft Measurement Method for Cement Clinker fcao Based on Time Series Single-Dimensional Convolutional Nearual Network [J]. Acta Metrologica Sinica, 2020, 41(9): 1152-1162.
	JIN H L, MA W X, MENG Z, et al. An Improved 1DCNN-GRU for Rolling Bearing Fault Diagnosis[J]. Acta Metrologica Sinica, 2023, 44(9): 1423-1428.
[22]	VIDYA S, JAGANNATHAN V, GUHAN T, et al. Long-Term and Short-Term Rainfall Forecasting Using Deep Neural Network Optimized with Flamingo Search Optimization Algorithm [J]. Journal of Intelligent & Fuzzy Systems, 2024, 46(1): 543-561.
	XING T T, GUAN Y, SUN D Y, et al. Rolling Bearing Fault Diagnosis Based on Clustering by Fast Search and Find Density Peaks Combined OTSU Method [J]. Acta Metrologica Sinica, 2021, 42(11): 1466-1471.
	ZHANG Y Y, LU Y, ZHAO J. Fault Diagnosis System of Numerical Control Machine Based on Incremental Learning [J]. Acta Metrologica Sinica, 2022, 43(11): 1456-1463.
	LAI R S, YAN G Q. Review of Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network [J]. Journal of Mechanical & Electrical Engineering, 2024, 41(2): 194-204.
[9]	IQBAL M, MADAN A K. CNC Machine-Bearing Fault Detection Based on Convolutional Neural Network Using Vibration and Acoustic Signal [J]. Journal of Vibration Engineering & Technologies, 2022, 10(5): 1613-1621.
[16]	GAO J, SONG Q H, LIU Z Q, et al. Chatter Detection and Stability Region Acquisition in Thin-Walled Workpiece Milling Based on CMWT [J]. International Journal of Advanced Manufacturing Technology, 2018, 98(1-4): 699- 713.
	LI T H, LI Z X, WANG Y X. Research on Intelligent Diagnosis of Bearing Faults Based on Improved Chaosnet with Small Samples [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2024(2): 182-185, 192.
[14]	ZHAO X L, YAO J Y, DENG W X, et al. Multiscale Deep Graph Convolutional Networks for Intelligent Fault Diagnosis of Rotor-Bearing System Under Fluctuating Working Conditions [J]. IEEE Transactions on Industrial Informatics, 2023, 19(1): 166-176.
	XIAO B, GUO J W, ZHANG X P, et al. Fine-Grained Visual Classification Network Based on Fusion Pooling and Attention Enhancement [J]. Pattern Recognition and Artificial Intelligence, 2023, 36(7): 661-670.
	LIU G X, HUANG J. Transfer Learning Techniques for Semantic Segmentation of Machine Vision Inspection and Identification Based on Label-Reserved Softmax Algorithms [J]. Optics and Precision Engineering, 2022, 30(1): 117-125.
	ZHU Q B, SHI C, LI L. Steel Defect Detection Based on Adam Active Decay Annealing Algorithm [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023(1): 92-95, 100.
[19]	金海龙, 马吴旭,孟宗, 等. 基于改进1DCNN-GRU的滚动轴承故障诊断[J]. 计量学报, 2023, 44(9): 1423-1428.