基于时频图与改进图卷积神经网络的异步电机故障诊断方法

摘要
图/表
参考文献(23)
相关文章 (15)

全文: PDF (1951 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要由于传统故障诊断技术依赖于人工提取特征，造成方法的泛化能力及其应用受限。针对该问题，本文提出一种基于时频图与改进图卷积神经网络的异步电机故障诊断方法。首先，通过小波分析方法将电机振动信号转换为时频图，构建不同工况的图像样本；再基于超像素分割法处理图像生成超像素块，将其作为节点，并根据其纹理、颜色、距离特征生成图结构数据；然后将图结构数据输入改进网络，算法可以自适应地提取故障特征、得到诊断结果。其中，网络通过结构学习方法进行改进，该方法通过对节点相似度计算打分，以重构图连接结构，从而克服传统图卷积神经网络在池化操作后存在的图结构的完整性缺失问题，实现卷积层和池化层的层层堆叠，实现图级分类。试验结果表明所提出方法可以实现对转子断条故障、轴承故障、单相短路故障的有效诊断，与文中提及的传统方法相比，具有较高的故障识别准确率。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈起磊1
	蒋亦悦1
	唐瑶2
	张晓飞2
	王朝红1

关键词 ：异步电机, 故障诊断, 图神经网络, 小波变换, 振动信号, 结构学习

Abstract：The traditional fault diagnosis methods rely on the handcraft feature extraction, so its performance highly depends on the expert knowledge and its application is limited. To solve this problem, a fault diagnosis method based on time-frequency image method and improved Graph Convolutional Network (GCN) is proposed in this paper. Firstly, the vibration signals are transformed into time-frequency images by the wavelet transform method. Then, based on the simple linear iterative clustering (SLIC), the images are segmented adaptively to generate superpixels, which are regarded as nodes in the graph. Next, based on the color and texture features in the superpixels, the connection relationships and the node features are formed. Then, the graphs are input into the network to diagnose the fault type. The algorithm can extract the features automatically and make the diagnostic classification. To overcome the limitations in traditional GCN, the network is improved by the structure learning method. This method reconstructs the connect relationship by calculating the similarity between nodes, thereby keeping the structure integrity after pooling. By stacking the convolutional and pooling operations, the diagnosis can be realized in graph level. The results show that the proposed method can effectively classify different motor statuses under varying working condition, and the fault detection accuracy is the highest compared with the traditional deep learning method in the paper.

收稿日期: 2021-09-17 出版日期: 2022-12-28

引用本文:

陈起磊1，蒋亦悦1，唐瑶2，张晓飞2，王朝红1. 基于时频图与改进图卷积神经网络的异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24): 241-248.
CHEN Qilei1, JIANG Yiyue1, TANG Yao2, ZHANG Xiaofei2, WANG Zhaohong1. An induction motor fault diagnosis method based on the time-frequency image method and an improved graph convolutional network. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(24): 241-248.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2022/V41/I24/241

[1] 耿晓强,唐向红,陆见光.基于云加端的电机轴承故障诊断应用研究[J].振动与冲击,2019,38(09):223-230.
GENG Xiaoqiang, TANG Xianghong, LU Jianguang. Application of motor bearing fault diagnosis based on cloud and terminal [J]. Journal of vibration and shock, 2019, 38(9): 223-230.
[2] CHOI S, PAZOUKI E, BAEK J, et al. Iterative Condition Monitoring and Fault Diagnosis Scheme of Electric Motor for Harsh Industrial Application [J], IEEE Transactions on Industrial Electronics,2015, 62(3):1760-1769.
[3] SAPENA-BAÑÓ A, PINEDA-SANCHEZ M, PUCHE-PANADERO R, et al. Fault Diagnosis of Rotating Electrical Machines in Transient Regime Using a Single Stator Current’s FFT [J], IEEE Transactions on Instrumentation and Measurement, 2015, 64(11): 3137-3146
[4] MAQSOOD, OSLEBO D, CORZINE K, et al, STFT Cluster Analysis for DC Pulsed Load Monitoring and Fault Detection on Naval Shipboard Power Systems [J], IEEE Transactions on Transportation Electrification, 2020, 6(2): 821-831.
[5] YANG B, LIU R and CHEN X, Sparse Time-Frequency Representation for Incipient Fault Diagnosis of Wind Turbine Drive Train [J], IEEE Transactions on Instrumentation and Measurement , 2018,67(11): 2616-2627.
[6] HU Q, QIN A, ZHANG Q, et al, Fault Diagnosis Based on Weighted Extreme Learning Machine With Wavelet Packet Decomposition and KPCA [J], IEEE Sensors Journal , 2018, 18(20):8472-8483.
[7] 鄢仁武,林穿,高硕勋,等.基于小波时频图和卷积神经网络的断路器故障诊断分析[J].振动与冲击,2020,39(10):198-205.
YAN RenwuYan, LIN chuan, GAO shuoxun, et al. Fault diagnosis and analysis of circuit breaker based on wavelet time-frequency representations and convolution neural network [J]. Journal of Vibration and Shock, 2020,39(10):198-205.
[8] 张安安,黄晋英,冀树伟,李东.基于卷积神经网络图像分类的轴承故障模式识别[J].振动与冲击,2020,39(04):165-171.
ZHANG Anan, HUANG Jinying, JI Shuwei, et al. Bearing fault pattern recognition based on image classification with CNN [J]. Journal of vibration and shock, 2020,39(04):165-171.
[9] DING X, HE Q, SHAO Y, et al, Transient Feature Extraction Based on Time–Frequency Manifold Image Synthesis for Machinery Fault Diagnosis [J], IEEE Transactions on Instrumentation and Measurement, 2019, 68(11): 4242-4252.
[10] ZHAO X, JIA M, and LIU Z, et al. Semi-Supervised Graph Convolution Deep Belief Network for Fault Diagnosis of Electormechanical System with Limited Labeled Data [J], IEEE Transactions on Industrial Informatics, 2020: 1551-3203.
[11] Zhao X, LIU Z, WANG T, et al. Unsupervised Fault Diagnosis of Machine via Multiple-Order Graphical Deep Extreme Learning Machine [C]// 2020 Asia-Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM), 2020.
[12] ZHANG D C, STEWART E, ENTEZAMI M, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network – ScienceDirect[J]. Measurement, 2020, 156.
[13] ZHANG Z, BU J, ESTER M, et al. Hierarchical Graph Pooling with Structure Learning [EB/OL]. https://arxiv.org/abs/ 1911.05954, 2019.
[14] RAHMANI M and ATIA G. K, Innovation Pursuit: A New Approach to Subspace Clustering [J], IEEE Transactions on Signal Processing , 65(23): 6276-6291.
[15] SCARSELLI F, GORI M, TSOI A. C, et al. The Graph Neural Network Model [J], IEEE Transactions on Neural Networks , 2009, 20(1): 61-80.
[16] SCARDAPANE S, SPINELLI. Spinelli and LORENZO P. D, Distributed Training of Graph Convolutional Networks [J], IEEE Transactions on Signal and Information Processing over Networks , 2021, 7: 87-100.
[17] LECUN Y and BOTTOU L, Gradient-based learning applied to document recognition [J], Proceedings of IEEE, 1998, 86(11): 2278-2324.
[18] HOCHREITER S and JC SCHMIDHUBER, Long short-term memory [J], Neural Computer , 1997, 9(8): 1735-80.
[19] PAL SK and MITRA S M, Multilayer perceptron, fuzzy sets, and classification [J], IEEE Transaction. Neural Network , 1992, 3(5): 683-97.
[20] 吴文开,徐明强,王树青,蒋玉峰,王国兴.考虑环境因素影响的海洋平台结构损伤检测研究[J].振动与冲击,2021,40(16):294-302.
WU Wenkai, XU Mingqiang, WANG Shuqing, et al. Structural damage detection of offshore platforms considering environmental variations [J]. Journal of vibration and shock, 2021,40(16):294-302.
[21] 史光宇,徐健,杨强.基于卷积神经网络的风电机组轴承机械故障智能诊断方法[J].华北电力大学学报(自然科学版),2020,47(04):71-79.
SHI Guangyu, XU Jian, YANG Qiang. Intelligent Fault Diagnosis on Wind Turbine Bearing Based on Convolutional Neural Network [J]. Journal of North China Electric Power University(Natural Science Edition) ,2020,47(04):71-79.
[22] 王宏超,杜文辽.基于强抗噪威格纳威利分析的滚动轴承故障诊断[J].航空动力学报,2019,34(04):772-777.
WANG Hongchao, DU Wenliao. Fault diagnosis of rolling bearing based on noise-resistant Wigner-Vile analysis [J]. Journal of aerospace power, 2019,34(04):772-777.
[23] XIONG J, LI C, WANG C, et al. Application of convolutional neural network and data pre-processing by mutual dimensionless and similar Gram matrix in fault diagnosis [J], IEEE Transactions on Industrial Informatics , 2021.