Rolling bearing fault diagnosis based on RegNet-CSAM and ZOA-KELM model

PDF(3944 KB)

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (11) : 165-175.

QI Xiaoli, WANG Zhaojun, MAO Junyi, WANG Zhiwen, CUI Dehai, ZHAO Fangxiang

Author information +

History +

Abstract

To address the issues of poor diagnostic performance and high computational complexity in existing deep convolutional neural network models for rolling bearing fault diagnosis, a novel model based on RegNet-CSAM and ZOA-KELM is proposed. Firstly, the attention mechanism CSAM that combines channel and spatial features is combined with the group convolution residual module to improve the representation ability of the structure. The RegNet-CSAM network constructed thus has a model complexity of 0.48GF; Secondly, during the classification stage, the Zebra Optimization Algorithm-based Kernel Extreme Learning Machine (ZOA-KELM) is used to replace the original Softmax function in the network to accomplish the final classification task. Experimental results for rolling bearing fault diagnosis indicate that the RegNet network is prone to misjudge some samples with mixed faults. The integration of CSAM into the RegNet network improves the accuracy by 0.5%, but does not effectively address the problem of misjudgment for mixed faults. However, by employing ZOA-KELM to replace the Softmax function for feature classification in the RegNet-CSAM network, it can effectively identify both single and mixed rolling bearing faults, achieving an accuracy rate of 99.92%. Compared with other networks, the proposed method can improve the diagnosis accuracy by up to 5.02%, and reduce the model complexity by up to 32 times.

Key words

Fault diagnosis / Rolling bearing / Group convolution residual structure / Attention mechanism / Zebra Optimization Kernel Extreme Learning Machine

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

QI Xiaoli, WANG Zhaojun, MAO Junyi, WANG Zhiwen, CUI Dehai, ZHAO Fangxiang. Rolling bearing fault diagnosis based on RegNet-CSAM and ZOA-KELM model[J]. Journal of Vibration and Shock, 2024, 43(11): 165-175

References

[1] 樊红卫,张旭辉,曹现刚等.智慧矿山背景下我国煤矿机械故障诊断研究现状与展望[J].振动与冲击,2020,39(24):194-204. FAN Hongwei, ZHANG Xuhui, CAO Xiangang, et al. Current status and prospect of my country's coal mine machinery fault diagnosis research under the background of smart mines [J]. Journal of Vibration and Shock, 2020,39(24):194-204. [2] 王平,廖明夫.滚动轴承故障诊断的自适应共振解调技术[J].航空动力学报,2005,20(04):606-612. Wang Ping, Liao Mingfu. Adaptive resonance demodulation technology for rolling bearing fault diagnosis [J]. Journal of Aerospace Power, 2005,20(04):606-612. [3] Auger F, Chassande-Mottin E, Flandrin P. On Phase-Magnitude Relationships in the Short-Time Fourier Transform [J]. IEEE Signal Processing Letters, 2012, 19(5): 267-270. [4] 陈是扦,彭志科,周鹏.信号分解及其在机械故障诊断中的应用研究综述[J].机械工程学报,2020, 56(17):91-107. Chen Shixu, Peng Zhike, Zhou Peng. A review of signal decomposition and its application in mechanical fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2020,56(17) :91-107. [5] Yang H, Li X, Zhang W. Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis[J]. Measurement Science and Technology, 2022, 33(5): 055005. [6] 肖雄, 王健翔, 张勇军, 等. 一种用于轴承故障诊断的二维卷积神经网络优化方法[J]. 中国电机工程学报, 2019, 39(15): 4558-4568. Xiao X, Wang J X, Zhang Y J, et al. A two-dimensional convolutional neural network optimization method for bearing fault diagnosis[J]. Proceedings of the CSEE, 2019, 39(15): 4558-4567. [7] 赵小强,梁浩鹏.使用改进残差神经网络的滚动轴承变工况故障诊断方法[J].西安交通大学学报,2020,54(09):23-31. Zhao Xiaoqiang, Liang Haopeng. Fault diagnosis method for rolling bearings under variable working conditions using improved residual neural network [J]. Journal of Xi'an Jiaotong University, 2020, 54(09):23-31. [8] 丁汕汕,陈仁文,黄翊君等.重参数化VGG网络在滚动轴承故障诊断中的应用研究[J].振动与冲击,2023,42(11):313-323. Ding Shanshan, Chen Renwen, Huang Yijun, et al. Application Research of Reparameterized VGG Network in Fault Diagnosis of Rolling Bearings[J]. Journal of Vibration and Shock, 2023,42(11):313-323. [9] 黄大荣,陈长沙,赵玲,孙国玺,柯兰艳.滚动轴承复合故障的混合协同诊断方法[J].电子科技大学学报,2018, 47(06):853-863. Huang Darong, Chen Changsha, Zhao Ling, et al. Hybrid collaborative diagnosis method for complex faults of rolling bearings[J]. Journal of University of Electronic Science and Technology of China,2018, 47(06):853-863. [10] Chen S, Meng Y, Tang H, et al. Robust deep learning-based diagnosis of mixed faults in rotating machinery[J]. IEEE/ASME Transactions on Mechatronics, 2020, 25(5): 2167-2176. [11] 邓飞跃,吕浩洋,顾晓辉,等.基于轻量化神经网络Shuffle-SENet的高速动车组轴箱轴承故障诊断方法[J].吉林大学学报(工学版),2022,52(02):474-482. Deng Feiyue, Lv Haoyang, Gu Xiaohui, et al. Fault diagnosis method for high-speed EMU axlebox bearings based on lightweight neural network Shuffle-SENet [J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(02): 474-482. [12] Yao D, Li G, Liu H, et al. An intelligent method of roller bearing fault diagnosis and fault characteristic frequency visualization based on improved MobileNet V3[J]. Measurement Science and Technology, 2021, 32(12): 124009. [13] Yu W, Lv P. An end-to-end intelligent fault diagnosis application for rolling bearing based on MobileNet[J]. IEEE Access, 2021, 9: 41925-41933. [14] Radosavovic I, Kosaraju R P, Girshick R, et al. Designing network design spaces[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10428-10436. [15] 杜甜甜,南新元,黄家興等.改进RegNet识别多种农作物病害受害程度[J].农业工程学报,2022,38(15):150-158. Du Tiantian, Nan Xinyuan, Huang Jiaxing, et al. Improved RegNet to identify the damage degree of various crop diseases [J]. Journal of Agricultural Engineering, 2022,38(15):150-158. [16] Chen Y, Sharifuzzaman SASM, Wang H, et al. Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet[J]. Computers, Materials & Continua, 2023, 75(3). 5451-5469. [17] 尹文哲,夏虹,彭彬森等.基于CNN-SVM的核电厂轴承故障诊断方法[J].哈尔滨工程大学学报,2023,44(03):410-417. Yin Wenzhe, Xia Hong, Peng Binsen, et al. CNN-SVM-based bearing fault diagnosis method for nuclear power plants[J]. Journal of Harbin Engineering University, 2023,44(03):410-417. [18] 程军圣, 于德介, 邓乾旺,等. 连续小波变换在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2003, 14(23): 2037-2040. Cheng Junsheng, Yu Dejie, Deng Qianwang, et al. Application of Continuous Wavelet Transform in Fault Diagnosis of Rolling Bearings[J]. China Mechanical Engineering, 2003, 14(23): 2037-2040. [19] Gu X, Yang S, Liu Y, et al. Compound faults detection of the rolling element bearing based on the optimal complex Morlet wavelet filter[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2018, 232(10): 1786-1801. [20] 王松,纪鹏,张云洲等.自适应感受野网络的行人重识别[J].控制与决策,2022,37(01):119-126. Wang Song, Ji Peng, Zhang Yunzhou, et al. Pedestrian re-identification with adaptive receptive field network[J]. Control and Decision, 2022, 37(01): 119-126. [21] Zhao M, Zhong S, Fu X, et al. Deep residual networks with adaptively parametric rectifier linear unitsfor fault diagnosis[J]. IEEE transactions on industrial electronics, 2020, 68(3): 2587-2597. [22] Roy S K, Dubey S R, Chatterjee S, et al. FuSENet: fused squeeze‐and‐excitation network for spectral‐spatial hyperspectral image classification[J]. IET Image Processing, 2020, 14(8): 1653-1661. [23] Chen J, Wan L, Zhu J, et al. Multi-scale spatial and channel-wise attention for improving object detection in remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 17(4): 681-685. [24] Zheng Y, Chen B, Wang S, et al. Mixture Correntropy-Based Kernel Extreme Learning Machines[J]. IEEE Transactions on Neural Networks and Learning Systems,2022. 33(2):811-825. [25] Chen P , Zhao X , Zhu Q .A novel classification method based on ICGOA-KELM for fault diagnosis of rolling bearing[J]. Applied Intelligence: The International Journal of Artificial Intelligence, NeuralNetworks, and Complex Problem-Solving Technologies, 2020,50(9):2833-2847. [26] Trojovská E, Dehghani M, Trojovský P. Zebra optimization algorithm: A new bio-inspired optimization algorithm for solving optimization algorithm[J]. IEEE Access, 2022, 10: 49445-49473. [27] Yang J, Bagavathiannan M, Wang Y, et al. A comparative evaluation of convolutional neural networks, training image sizes, and deep learning optimizers for weed detection in Alfalfa[J]. Weed Technology, 2022, 36(4): 512-522. [28] 陈保家,陈学力,沈保明等.CNN-LSTM深度神经网络在滚动轴承故障诊断中的应用[J].西安交通大学学报,2021,55(06):28-36. Chen Baojia, Chen Xueli, Shen Baoming, et al. Application of CNN-LSTM Deep Neural Network in Fault Diagnosis of Rolling Bearings[J]. Journal of Xi'an Jiaotong University,2021,55(06):28-36.