基于双图转换和融合CRNN网络的轴承故障诊断

PDF(3560 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (19) : 240-248.

论文

李喆，吐松江•卡日，范想，范志鹏，万容齐，白新悦，吴俣潼

作者信息 +

Bearing fault diagnosis based on double-graph conversion and fusion CRNNs

LI Zhe, KARI Tusongjiang, FAN Xiang, FAN Zhipeng, WAN Rongqi, BAI Xinyue, WU Yutong

Author information +

文章历史 +

摘要

针对一维振动序列输入制约卷积神经网络性能，且单一数据处理方法限制实际复杂工况下轴承故障特性的深层挖掘等问题，提出了一种基于双图转换与多卷积循环神经网络融合的滚动轴承故障诊断方法。首先，分别利用格拉姆角差场和马尔可夫转移场编码方法将一维序列信号转换为二维图像。然后，将转换后的两种模态图像同时输入多CRNN融合的Fu-CRNN网络模型，充分汲取两种转换方法优点并提高CRNN模型特征表达能力。最后实现轴承信号特征自适应提取及端到端诊断。为验证该方法的可靠性与优越性，选用凯斯西储大学滚动轴承数据集进行轴承故障诊断试验，并比较分析诊断性能。结果表明，所提模型识别准确率和泛化效果均优于单一模态样本输入模型，相较于其他常用算法表现更出色，可为样本构建和轴承故障诊断方法提供参考。

Abstract

Aiming at the problems that one-dimensional vibration sequence input limits convolutional neural network performance, and the single data processing method restricts the deep mining of bearing fault characteristics under actual complex working conditions, a rolling bearing fault diagnosis method based on the fusion of double graph conversion and multiple convolutional recurrent neural network is proposed. Firstly, one-dimensional sequence signals are converted into two-dimensional images by using Gramian angular difference field and Markov transition field coding methods respectively. Then, the converted two modal images are simultaneously input into the Fu-CRNN network model of multi-CRNN fusion, fully absorbing the advantages of the two conversion methods and improving the feature expression ability of CRNN model. Finally, the adaptive feature extraction and end-to-end diagnosis of bearing signals are realized. To verify the reliability and superiority of this method, Case Western Reserve University rolling bearing data set is selected to set up bearing fault diagnosis experiments, and the diagnostic performance is compared with that of traditional methods. The results show that the recognition accuracy and generalization effect of the proposed model are better than those of single modal sample input model, and it is also better than other common algorithms, which can provide reference for sample construction and bearing fault diagnosis.

导出引用

李喆，吐松江卡日，范想，范志鹏，万容齐，白新悦，吴俣潼. 基于双图转换和融合CRNN网络的轴承故障诊断[J]. 振动与冲击, 2023, 42(19): 240-248

LI Zhe, KARI Tusongjiang, FAN Xiang, FAN Zhipeng, WAN Rongqi, BAI Xinyue, WU Yutong. Bearing fault diagnosis based on double-graph conversion and fusion CRNNs[J]. Journal of Vibration and Shock, 2023, 42(19): 240-248

参考文献

[1] 陈雪峰, 郭艳婕, 许才彬, 等. 风电装备故障诊断与健康监测研究综述[J]. 中国机械工程, 2020, 31(2): 175-189.
CHEN X F, GUO Y J, XU C B, et al. Summary of research on fault diagnosis and health monitoring of wind power equipment[J]. China mechanical engineering, 2020, 31(2): 175-189.
[2] RAI A, UPADHYAY S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International, 2016, 96: 289-306.
[3] 雷亚国, 贾峰, 周昕, 等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21), 49-56.
LEI Y G, JIA F, ZHOU X, et al. Big data health monitoring method of mechanical equipment based on deep learning theory[J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56.
[4] YUAN J, JIANG H M, ZHAO Q, et al. Dual-Mode Noise-Reconstructed EMD for Weak Feature Extraction and Fault Diagnosis of Rotating Machinery[J]. IEEE Access, 2019, 7: 173541-173548.
[5] LIU C C, ZHUO F, WANG F, Fault Diagnosis of Commutation Failure Using Wavelet Transform and Wavelet Neural Network in HVDC Transmission System[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-8.
[6] 钱林, 康敏, 傅秀清, 等. 基于VMD的自适应形态学在轴承故障诊断中的应用[J]. 振动与冲击, 2017, 36(3): 227-233.
QIAN L, KANG M, FU X Q, et al. Application of adaptive morphology in bearing fault diagnosis based on VMD[J]. Journal of Vibration and Shock, 2017, 36(3): 227-233.
[7] 吐松江•卡日, 高文胜, 张紫薇, 等. 基于支持向量机和遗传算法的变压器故障诊断[J]. 清华大学学报(自然科学版), 2018, 58(7): 623-629.
KARI•T S J, GAO W S, ZHANG Z W, et al. Power transformer fault diagnosis based on a support vector machine and a genetic algorithm[J]. Journal of Tsinghua University (Science and Technology), 2018, 58(7): 623-629.
[8] 贺立敏, 王岘昕, 韩冰. 基于随机森林和支持向量机的船舶柴油机故障诊断[J]. 中国航海, 2017, 40(2): 29-33.
HE L M, WANG X X, HAN B. Fault diagnosis of marine diesel engine based on random forest and support vector machine[J]. Navigation of China, 2017, 40(2): 29-33.
[9] TANG J, DENG C, G. Huang. Extreme Learning Machine for Multilayer Perceptron[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(4): 809-821.
[10] 曲建岭, 余路, 袁涛, 等. 基于一维卷积神经网络的滚动轴承自适应故障诊断算法[J]. 仪器仪表学报, 2018, 39(7): 134-143.
QU J L, YU L, YUAN T, et al. Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network[J]. Chinese Journal of Scientific Instrument, 2018, 39(7): 134-143.
[11] 李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19): 124-131.
LI H, ZHANG Q, QIN X R, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock, 2018, 37(19): 124-131.
[12] 袁建虎, 韩涛, 唐建, 等. 基于小波时频图和CNN的滚动轴承智能故障诊断方法[J]. 机械设计与研究, 2017, 33(02): 93-97.
YUAN J H, HAN T, TANG J, et al. An intelligent fault diagnosis method for rolling bearings based on wavelet time-frequency diagram and CNN[J] Machinery Design and Research, 2017, 33(2): 93-97.
[13] WEN L, LI X Y, GAO L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2017, 65(7): 5990-5998.
[14] 仝钰, 庞新宇, 魏子涵. 基于GADF-CNN的滚动轴承故障诊断方法[J]. 振动与冲击, 2021, 40(05): 247-253, 260.
TONG Y, PANG X Y, WEI Z H. A GADF-CNN based rolling bearing fault diagnosis method[J]. Vibration and Shock, 2021, 40(5): 247-253, 260.
[15] 雷春丽, 夏奔锋, 薛林林, 等. 基于MTF-CNN的滚动轴承故障诊断方法[J]. 振动与冲击, 2022, 41(09): 151-158.
LEI C Y, XIA B F, XUE L L, et al. Rolling bearing fault diagnosis method based on MTF-CNN[J]. Vibration and Shock, 2022, 41(09): 151-158.
[16] 张训杰, 张敏, 李贤均. 基于二维图像和CNN-BiGRU网络的滚动轴承故障模式识别[J]. 振动与冲击, 2021, 40(23): 194-201.
ZHANG X J, ZHANG M, LI X J. Rolling bearing fault mode recognition based on 2D image and CNN-BiGRU[J]. Vibration and Shock, 2021, 40(23): 194-201.
[17] WANG Z G, OATES T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[C]//Workshops at the Twenty-ninth AAAI Conference on Artificial Intelligence. Austin: AAAI, 2015.
[18] LIU X Z, CAI H X, ZHONG R X, et al. Learning traffic as images for incident detection using convolutional neural networks[J]. IEEE Access, 2020, 8: 7916-7924.
[19] LIU L, Wang Z. Encoding temporal markov dynamics in graph for visualizing and mining time series[C]//Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence. 2018.
[20] SHI B, BAI X, YAO C. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(11): 2298-2304.
[21] Case Western Reserve University. Bearing data center [EB/OL]. 2018. https://cse groups.case.edu/bearing data center/Pages/download-data-file.
[22] 姚立, 孙见君, 马晨波. 基于格拉姆角场和CNN-RNN的滚动轴承故障诊断方法[J]. 轴承, 2022(02): 61-67.
YAO L, SUN J J, MA C B, Fault diagnosis method for rolling bearings based on gramian angular fields and CNN-RNN[J]. Bearing, 2022(02): 61-67.
[23] 姜家国, 郭曼利. 基于GAF和DenseNet的滚动轴承故障诊断方法[J]. 工矿自动化, 2021, 47(08): 84-89.
JIANG J G, GUO M L. Fault diagnosis of rolling bearing based on GAF and DenseNet[J]. Instrumentation, 2021, 47(08): 84-89.
[24] 姜家国, 郭曼利. 基于MTF和DenseNet的滚动轴承故障诊断方法[J]. 工矿自动化, 2022, 48(09): 63-68.
JIANG J G, GUO M L. Fault diagnosis of rolling bearing based on MTF-DenseNet[J]. Instrumentation, 2022, 48(09): 63-68.