Identification of the lubrication state of journal bearings based on acoustic emission and WST-CNN collaboration

PDF(2365 KB)

Journal of Vibration and Shock ›› 2023, Vol. 42 ›› Issue (22) : 71-77.

LU Xuxiang，LIU Shunshun，CHEN Xiangmin，ZHANG Kang

Author information +

History +

Abstract

A method for lubrication state identification and fault diagnosis of journal bearings based on wavelet scattering transform and convolutional neural network was proposed to use acoustic emission signal to sensitively characterize the differential lubrication states of journal bearings. The optimized wavelet scattering network was used for automatic robust feature extraction of the acoustic emission signals of a journal bearing of a 310MW turbo-generator set, and the best feature matrix was input into the optimized convolutional neural network for lubrication state recognition and classification. The results show that the optimized wavelet scattering network can effectively extract the acoustic emission signal features, and combined with the optimized convolutional neural network to intelligently identify the feature matrix, the recognition rate of the lubrication states of the sliding bearing can reach 95.28%, and the lubrication states of the sliding bearing can be efficiently and accurately diagnosed.

Key words

acoustic emission / journal bearing / feature extraction / fault diagnosis / neural network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LU Xuxiang，LIU Shunshun，CHEN Xiangmin，ZHANG Kang. Identification of the lubrication state of journal bearings based on acoustic emission and WST-CNN collaboration[J]. Journal of Vibration and Shock, 2023, 42(22): 71-77

References

[1] 卢绪祥, 苏一鸣, 吴家腾, 等. 基于EMD及灰色关联度的滑动轴承润滑状态故障诊断研究[J]. 动力工程学报,2016, 36(01): 42-47.
LU Xuxiang, SU Yiming, WU Jiateng, et al. Fault diagnosis on lubrication state of journal bearings based on EMD and grey relational degree [J]. Journal of Chinese Society of Power Engineering, 2016, 36(01): 42-47.
[2] Babu N T, Himamshu H S, Kumar P N, et al. Journal bearing fault detection based on Daubechies wavelet[J]. Archives of Acoustics, 2017, 42(3):401-414.
[3] Babu N T, Aravind A, Rakesh A, et al. Automatic fault classification for journal bearings using ANN and DNN[J]. Archives of Acoustics, 2018, 43(4):727-738.
[4] Tang H, Liao Z, Ozaki Y, et al. Stepwise intelligent diagnosis method for rotor system with sliding bearing based on statistical filter and stacked auto-encoder[J]. Applied Sciences, 2020, 10(7): 2477.
[5] König F.,Sous C.,Ouald Chaib A.,Jacobs G.. Machine learning based anomaly detection and classification of acoustic emission events for wear monitoring in sliding bearing systems[J]. Tribology International,2021,155.
[6] Honglin L, Lin B, Chang P,et al. An improved convolutional-neural-network-based fault diagnosis method for the rotor–journal bearings system[J]. Machines, 2022, 10(7):503.
[7] 朱益军, 李录平, 靳攀科, 等. 滑动轴承润滑状态与声发射信号特征关系研究[J]. 汽轮机技术,2011, 53(01): 50-52.
ZHU Yijun, LI Luping, JIN Panke, et al. Research on the relationship between characteristic of AE signal and hydrodynamic bearing fault [J]. Turbine Technology, 2011, 53(01): 50-52.
[8] 王晓伟, 刘占生, 张广辉, 等. 基于声发射的可倾瓦径向滑动轴承碰摩故障诊断[J]. 中国电机工程学报,2009, 29(08): 64-69.
WANG Xiaowei, LIU Zhansheng, ZHANG Guanghui, et al. Rubbing fault diagnose of tilting pad journal bearing by acoustic emission [J]. Proceedings of the CSEE,2009, 29(08): 64-69.
[9] 靳攀科, 李录平, 谭海辉, 等. 310MW汽轮发电机组启动过程中滑动轴承声发射信号特性试验[J]. 汽轮机技术,2011, 53(06): 455-458.
JIN Panke, LI Luping, TAN Haihui, et al. Characteristics of sliding bearing acoustic emission trial during the startup of 310MW steam turbine [J]. Turbine Technology,2011, 53(06): 455-458.
[10] 卢绪祥, 刘雨佳, 唐晟锟, 等. 滑动轴承声发射信号分形特征提取及故障诊断研究[J]. 湖南电力,2015, 35(04): 64-68.
LU Xuxiang, LIU Yujia, TANG Shengkun, et al. Study on fractal features extracted from acoustic emission signals and fault diagnosis of journal bearing [J]. Hunan Electric Power,2015, 35(04): 64-68.
[11] Vittoria B, Lucia C M, Domenico V. An MDL-based wavelet scattering features selection for signal classification[J]. Axioms, 2022, 11(8):376.
[12] 刘辉, 李永康, 高放, 等. 基于小波散射协同BiLSTM的输电线路故障诊断[J]. 国外电子测量技术,2021, 40(12): 165-172.
LIU Hui, LI Yongkang, GAO Fang, et al. Transmission line fault diagnosis based on wavelet scattering and BiLSTM [J]. Foreign Electronic Measurement Technology,2021, 40(12): 165-172.
[13] Varun K, H. A M, G. P M. Learnable wavelet scattering networks: applications to fault diagnosis of analog circuits and rotating machinery[J]. Electronics, 2022, 11(3):451.
[14] 文介华. 小波散射卷积神经网络及其应用图像检索[D]. 广州:广东工业大学, 2018.
[15] Yang J. Wavelet scattering and neural networks for railhead defect identification[J]. Materials, 2021, 14(8):1957.
[16] 樊鑫, 程建远, 王云宏, 等. 基于小波散射分解变换的煤矿微震信号智能识别[J]. 煤炭学报,2022, 47(07): 2722-2731.
FAN Xin, CHENG Jianyuan, WANG Yunhong, et al. Intelligent recognition of coal mine microseismic signal based on wavelet scattering decomposition transform [J]. Journal of China Coal Society,2022, 47(07): 2722-2731.
[17] 王冉,石如玉,胡升涵, 等 .基于声成像与卷积神经网络的轴承故障诊断方法及其可解释性研究[J].振动与冲击,2022,41(16):224-231.
Wang Ran, Shi Ruyu, Hu Shenghan, et al. An acoustic fault diagnosis method of rolling bearings based on acoustic imaging and convolutional neural network [J]. Journal of Vibration and Shock, 2022, 41(16): 224-231.