[1]李飞龙,和伟辉,刘立芳,等.结合CWT和LightweightNet的滚动轴承实时故障诊断方法[J].智能系统学报,2023,18(3):496-505.[doi:10.11992/tis.202204020]
LI Feilong,HE Weihui,LIU Lifang,et al.Real time fault diagnosis method of rolling bearing based on CWT and LightweightNet[J].CAAI Transactions on Intelligent Systems,2023,18(3):496-505.[doi:10.11992/tis.202204020]
点击复制
LI Feilong,HE Weihui,LIU Lifang,et al.Real time fault diagnosis method of rolling bearing based on CWT and LightweightNet[J].CAAI Transactions on Intelligent Systems,2023,18(3):496-505.[doi:10.11992/tis.202204020]
结合CWT和LightweightNet的滚动轴承实时故障诊断方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第3期
页码:
496-505
栏目:
学术论文—机器感知与模式识别
出版日期:
2023-07-05
- Title:
- Real time fault diagnosis method of rolling bearing based on CWT and LightweightNet
- Keywords:
- rolling bearing; fault diagnosis; continuous wavelet transform; time-frequency feature; lightweight neural network; group convolution; channel shuffle; inverted residual structure
- 分类号:
- TP183
- 摘要:
- 针对普通的深度学习算法用于轴承故诊断分类时计算量大、消耗成本高的问题，提出一种结合连续小波变换和轻量级神经网络的滚动轴承实时故障诊断方法。首先，使用Morlet母小波函数对轴承振动加速度数据进行连续小波变换，提取出时频域特征并将一维信号转换成二维图片；然后，结合分组卷积、通道混洗、倒残差结构等轻量级神经网络设计元素设计一个轻量级卷积神经网络LightweightNet用于时频图片的故障分类，LightweightNet网络在保证具有足够特征提取能力的同时还具有轻量级特点。使用凯斯西储大学轴承故障数据集进行实验表明，本方法相比于其他使用经典轻量级神经网络的方法具有更少的参数、最高的准确率和更快的诊断速度，基本可以实现滚动轴承的实时故障诊断，且在内存消耗与模型存储占用空间方面远小于其他同类方法。
- Abstract:
- In order to solve the problem of large computation and high cost when common deep learning algorithm is applied to bearing fault diagnosis and classification, a real-time rolling bearing fault diagnosis method combining continuous wavelet transform and lightweight neural network is proposed in this paper. Firstly, the Morlet mother wavelet function is used to carry out continuous wavelet transform on the bearing vibration acceleration data, extracting the time-frequency domain features and converting the one-dimensional signals into two-dimensional images. Then, LightweightNet, a lightweight convolutional neural network, is designed for time-frequency image fault classification by combining lightweight neural network design elements such as group convolution, channel shuffle and inverted residual structure. LightweightNet not only ensures sufficient feature extraction ability, but also has lightweight characteristics. The bearing failure experiment data sets from Case Western Reserve University show that, compared with other methods using classic lightweight neural network, this method has less parameters, the highest degree of accuracy and faster diagnosis speed, the real-time fault diagnosis of rolling bearing can be achieved basically, far less than other similar methods in memory consumption and model storage space.
- 参考文献/References:
-
[1] LI Chuan, DE OLIVEIRA J V, CERRADA M, et al. A systematic review of fuzzy formalisms for bearing fault diagnosis[J]. IEEE transactions on fuzzy systems, 2019, 27(7): 1362–1382.
[2] 姚峰林, 谢长开, 吕世宁, 等. 基于小波包变换和ELM的滚动轴承故障诊断研究[J]. 安全与环境学报, 2021, 21(6): 2466–2472
YAO Fenglin, XIE Changkai, LYU Shining, et al. Research on fault diagnosis of rolling bearings based on wavelet packet transform and ELM[J]. Journal of safety and environment, 2021, 21(6): 2466–2472
[3] 陈仁祥, 周君, 胡小林, 等. 基于深度Q学习和连续小波变换的旋转机械故障诊断方法[J]. 振动工程学报, 2021, 34(5): 1092–1100
CHEN Renxiang, ZHOU Jun, HU Xiaolin, et al. Fault diagnosis method of rotating machinery based on deep Q-learning and continuous wavelet transform[J]. Journal of vibration engineering, 2021, 34(5): 1092–1100
[4] WANG Xin, MAO Dongxing, LI Xiaodong. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network[J]. Measurement, 2021, 173: 108518.
[5] 潘琳鑫, 巩永旺, 晏生莲. 基于改进一维卷积神经网络的轴承故障诊断方法[J/OL]. 软件导刊: 1?5.[2023?04?05].http://kns.cnki.net/kcms/detail/42.1671.TP.20221207.1119.014.html.
Pan Linxin, Gong Yongwang, Yan Shenglian. A bearing fault diagnosis method based on improved one-dimensional convolutional neural network [J/OL]. Software Guide: 1?5.[2023?04?05].http://kns.cnki.net/kcms/detail/42.1671.TP.20221207.1119.014.html.
[6] YANG Zhibo, ZHANG Junpeng, ZHAO Zhibin, et al. Interpreting network knowledge with attention mechanism for bearing fault diagnosis[J]. Applied soft computing, 2020, 97: 106829.
[7] ZOU Fengqian, ZHANG Haifeng, SANG Shengtian, et al. An anti-noise one-dimension convolutional neural network learning model applying on bearing fault diagnosis[J]. Measurement, 2021, 186: 110236.
[8] ZHAO Jing, YANG Shaopu, LI Qiang, et al. A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network[J]. Measurement, 2021, 176: 109088.
[9] BAI Ruxue, XU Quansheng, MENG Zong, et al. Rolling bearing fault diagnosis based on multi-channel convolution neural network and multi-scale clipping fusion data augmentation[J]. Measurement, 2021, 184: 109885.
[10] 高淑芝, 裴志明, 张义民. 动态自适应学习率优化的卷积神经网络轴承故障诊断方法[J/OL]. 机械设计与制造: 1?5.[2023?04?05].DOI:10.19356/j.cnki.1001-3997.20230210.031.
GAO Shuzhi, PEI Zhiming, ZHANG Yimin. Dynamic adaptive learning rate optimized convolutional neural network bearing fault diagnosis method [J/OL]. Mechanical design and manufacturing: 1?5.[2023?04?05].DOI:10.19356/j.cnki.1001-3997.20230210.031.
[11] 李欢, 吕勇, 袁锐, 等. 基于深度卷积神经网络的滚动轴承迁移故障诊断[J]. 组合机床与自动化加工技术, 2023(2): 90–94
LI Huan, LYU Yong, YUAN Rui, et al. Fault diagnosis of rolling bearing migration based on deep convolution neural network[J]. Modular machine tool and automatic processing technology, 2023(2): 90–94
[12] MENG Zong, ZHAN Xuyang, LI Jing, et al. An enhancement denoising autoencoder for rolling bearing fault diagnosis[J]. Measurement, 2018, 130: 448–454.
[13] CLAESSENS B J, VRANCX P, RUELENS F. Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control[J]. IEEE transactions on smart grid, 2018, 9(4): 3259–3269.
[14] ZOU Yisheng, LIU Yongzhi, DENG Jialin, et al. A novel transfer learning method for bearing fault diagnosis under different working conditions[J]. Measurement, 2021, 171: 108767.
[15] HAO Shijie, GE Fengxiang, LI Yanmiao, et al. Multisensor bearing fault diagnosis based on one-dimensional convolutional long short-term memory networks[J]. Measurement, 2020, 159: 107802.
[16] XU Zifei, MEI Xuan, WANG Xinyu, et al. Fault diagnosis of wind turbine bearing using a multi-scale convolutional neural network with bidirectional long short term memory and weighted majority voting for multi-sensors[J]. Renewable energy, 2022, 182: 615–626.
[17] WU Zhenghong, JIANG Hongkai, LIU Shaowei, et al. A deep reinforcement transfer convolutional neural network for rolling bearing fault diagnosis[J]. ISA transactions, 2022, 129: 505–524.
[18] XU Yang, LI Zhixiong, WANG Shuqing, et al. A hybrid deep-learning model for fault diagnosis of rolling bearings[J]. Measurement, 2021, 169: 108502.
[19] PENG Xu, ALEXANDER H K. RALF B, et al. Measurement of the topological Chern number by continuous probing of a qubit subject to a slowly varying Hamiltonian[EB/OL]. (2017?04?03)[2022?04?12].https://arxiv.org/abs/1704.0486.
[20] ZHANG Xiangyu, ZHOU Xinyu, LIN Mengxiao, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6848?6856.
[21] YAO Dechen, LIU Hengchang, YANG Jianwei, et al. A lightweight neural network with strong robustness for bearing fault diagnosis[J]. Measurement, 2020, 159: 107756.
[22] SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510?4520.
[23] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770?778.
[24] XIE Saining, GIRSHICK R, DOLLáR P, et al. Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 5987?5995.
[25] SMITH W A, RANDAL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical Systems and Signal Processing, 2015(64-65): 100–131.
- 相似文献/References:
-
[1]马大中,张化光,冯 健,等.一种基于多传感器信息融合的故障诊断方法[J].智能系统学报,2009,4(1):72.
MA Da-zhong,ZHANG Hua-guang,FENG Jian,et al.A fault diagnosis method based on multi-sensor information fusion[J].CAAI Transactions on Intelligent Systems,2009,4():72.
[2]齐俊桐,韩建达.旋翼飞行机器人故障诊断与容错控制技术综述[J].智能系统学报,2007,2(2):31.
QI Jun-tong,HAN Jian-da.Fault diagnosis and faulttolerant control of rotorcraft flying robots: a survey[J].CAAI Transactions on Intelligent Systems,2007,2():31.
[3]李红芳,等.一种新型免疫网络学习算法在故障诊断中的应用[J].智能系统学报,2008,3(5):449.
L IHong-fang,ZHANG Qing-hua,et al.Application of a novel immune network learn ing algor ithm to fault diagnosis[J].CAAI Transactions on Intelligent Systems,2008,3():449.
[4]曲彦光,张勤,朱群雄.动态不确定因果图在化工系统动态故障诊断中的应用[J].智能系统学报,2015,10(3):354.[doi:10.3969/j.issn.1673-4785.201503012]
QU Yanguang,ZHANG Qin,ZHU Qunxiong.Application of dynamic uncertain causality graph to dynamic fault diagnosis in chemical processes[J].CAAI Transactions on Intelligent Systems,2015,10():354.[doi:10.3969/j.issn.1673-4785.201503012]
[5]文天柱,许爱强,邓露.可拓否定选择算法及其在故障诊断中的应用[J].智能系统学报,2015,10(3):488.[doi:10.3969/j.issn.1673-4785.201402020]
WEN Tianzhu,XU Aiqiang,DENG Lu.A new negative selection algorithm based on Extenics and its application in fault diagnosis[J].CAAI Transactions on Intelligent Systems,2015,10():488.[doi:10.3969/j.issn.1673-4785.201402020]
[6]杨佳婧,张勤,朱群雄.动态不确定因果图在化工过程故障诊断中的应用[J].智能系统学报,2014,9(2):154.[doi:10.3969/j.issn.1673-4785.201402012]
YANG Jiajing,ZHANG Qin,ZHU Qunxiong.Application of Dynamic Uncertain Causality Graphto fault diagnosis in chemical processes[J].CAAI Transactions on Intelligent Systems,2014,9():154.[doi:10.3969/j.issn.1673-4785.201402012]
[7]张龙,陈宸,韩宁,等.压缩感知理论中的建筑电气系统故障诊断[J].智能系统学报,2014,9(2):204.[doi:10.3969/j.issn.1673-4785.201310026]
ZHANG Long,CHEN Chen,HAN Ning,et al.Fault diagnosis of electrical systems in buildingsbased on compressed sensing[J].CAAI Transactions on Intelligent Systems,2014,9():204.[doi:10.3969/j.issn.1673-4785.201310026]
[8]夏飞,马茜,张浩,等.改进D-S证据理论在电动汽车锂电池故障诊断中的应用[J].智能系统学报,2017,12(4):526.[doi:10.11992/tis.201605001]
XIA Fei,MA Xi,ZHANG Hao,et al.Application of improved D-S evidence theory in fault diagnosis of lithium batteries in electric vehicles[J].CAAI Transactions on Intelligent Systems,2017,12():526.[doi:10.11992/tis.201605001]
[9]齐小刚,牛红曼,刘兴成,等.多层信息网络故障定位综述[J].智能系统学报,2019,14(1):44.[doi:10.11992/tis.201804062]
QI Xiaogang,NIU Hongman,LIU Xingcheng,et al.Survey of fault localization in multilayer information networks[J].CAAI Transactions on Intelligent Systems,2019,14():44.[doi:10.11992/tis.201804062]
[10]张婷,齐小刚.移动通信网络的中性集故障诊断方法研究[J].智能系统学报,2020,15(5):864.[doi:10.11992/tis.201906031]
ZHANG Ting,QI Xiaogang.Research on neutral set fault diagnosis method for mobile communication networks[J].CAAI Transactions on Intelligent Systems,2020,15():864.[doi:10.11992/tis.201906031]
备注/Memo
收稿日期:2022-04-12。
作者简介:李飞龙,硕士研究生,主要研究方向为数据处理与分析、装备故障诊断和故障预测;和伟辉,硕士研究生,主要研究方向为健康管理与故障诊断;刘立芳,教授,博士,主要研究方向为数据处理与智能计算。主持完成国家自然科学基金青年项目、预研领域基金项目等,参与十三五预研项目、教育部–中国移动联合基金项目、自主可控软件示范项目、企业重大技术攻关项目等十余项
通讯作者:刘立芳.E-mail:lfliu@mail.xidian.edu.cn
更新日期/Last Update:
1900-01-01