Please wait a minute...
工程设计学报
Chinese Journal of Engineering Design  2024, Vol. 31 Issue (2): 137-150    DOI: 10.3785/j.issn.1006-754X.2024.03.212
Theory and Method of Mechanical Design     
Research on fault diagnosis method based on multi-discriminator auxiliary classifier generative adversarial network
Zihan YE1,2(),Zhonghua WANG1,2(),Chao JIANG1,2,Xin Lü1,2,Zhe ZHANG1,2
1.State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Hunan University, Changsha 410082, China
2.College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China
Download: HTML     PDF(2872KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

In extremely harsh working environments such as strong impacts, intense radiation and extremely high temperature, the fault modes of mechanical equipment are complex and varied, and it is very difficult to obtain sufficient and effective fault data, even difficult to achieve, so that the accuracy of fault diagnosis is limited, and subsequent maintenance and repair programs are difficult to be effectively developed.To solve this problem, a data enhancement algorithm for multi-discriminator auxiliary classifier generative adversarial network was proposed. By setting up 3 discriminators, 1 generator and adding independent classifier, a new auxiliary classifier generative adversarial network model was constructed. Aiming at the instability issue in the model's training, the Wasserstein distance was introduced to construct a new loss function, and the unilateral soft constraint regularization term with more stability was used to replace the original L2 gradient penalty term to solve the problem of model collapse. Building on this, an efficient channel attention mechanism was adopted to further improve the model's feature extraction capability. The proposed model was applied to extend the fault data set of mechanical equipment to assist the training of deep learning intelligent diagnosis model. Multiple fault data set expansion experiments showed that compared with the existing model, the new model could generate higher quality data, and the accuracy of fault diagnosis was further improved, so it had high application value.

Key words： multi-discriminator auxiliary classifier generative adversarial network      efficient channel attention mechanism      Lipschitz penalty      data augmentation      fault diagnosis     
Received: 30 October 2023      Published: 26 April 2024
CLC:  TP 277  
Corresponding Authors: Zhonghua WANG     E-mail: 240014070@qq.com;wangzh0946@hnu.edu.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Zihan YE
Zhonghua WANG
Chao JIANG
Xin Lü
Zhe ZHANG
Cite this article:

Zihan YE,Zhonghua WANG,Chao JIANG,Xin Lü,Zhe ZHANG. Research on fault diagnosis method based on multi-discriminator auxiliary classifier generative adversarial network. Chinese Journal of Engineering Design, 2024, 31(2): 137-150.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2024.03.212     OR     https://www.zjujournals.com/gcsjxb/Y2024/V31/I2/137


基于多判别器辅助分类器生成对抗网络的故障诊断方法研究

在强冲击、强辐射、极高温等极端恶劣的工作环境下，机械设备的故障模式复杂多样，获得充足且有效的故障数据变得非常困难甚至难以实现，以致故障诊断的准确性受限，后续检修维护方案难以有效制定。针对这一问题，提出了一种多判别器辅助分类器生成对抗网络的数据增强算法。通过设置3个判别器、1个生成器并添加独立的分类器，构建了新的辅助分类器生成对抗网络模型。针对在该模型训练中存在的不稳定性问题，通过引入Wasserstein距离构造新的损失函数，并采用稳定性更具优势的单边软约束正则化项替换原有的L2梯度惩罚项来解决模型崩溃问题；在此基础上，采用高效通道注意力机制来进一步提高模型的特征提取能力。将所提出的模型应用于扩充机械设备故障数据集，辅助深度学习智能诊断模型的训练。多个故障数据集扩充实验表明，与现有模型相比，新模型所生成数据的质量更高，故障诊断的准确率也得到进一步提高，因此具有较高的应用价值。


关键词： 多判别器辅助分类器生成对抗网络,  高效通道注意力机制,  Lipschitz（利普希茨）约束,  数据增强,  故障诊断 
Fig.1 Frames of GAN and ACGAN
Fig.2 Frame of MDACGAN
网络结构
Discriminator0Conv2D(32,3,2,same)+MaxPool2D(2,1,same)
Conv2D(64,3,2,same)+MaxPool2D(2,1,same)
Conv2D(128,3,2,same)+MaxPool2D(2,1,same)
Conv2D(256,3,2,same)+MaxPool2D(2,1,same)
GlobalAvgpool2D()
Dense(1)
Discriminator1Conv2D(64,3,2,same)+MaxPool2D(2,1,same)
Conv2D(128,3,2,same)+MaxPool2D(2,1,same)
Conv2D(256,3,2,same)+MaxPool2D(2,1,same)
Conv2D(512,3,2,same)+MaxPool2D(2,1,same)
GlobalAvgpool2D()
Dense(1)
Discriminator2Flatten()
Dense(256)+Dropout(0.2)
Dense(128)+Dropout(0.2)
Dense(64)+Dropout(0.2)
Dense(1)
GeneratorDense(8192)
Conv2Dtranspose(128,5,2,same)+BN()
Conv2Dtranspose(64,5,2,same)+BN()
Conv2Dtranspose(32,5,2,same)+BN()
Conv2Dtranspose(1,5,2,same)
ClassifierConv2D(32,3,2,same)+BN()+MaxPool2D(2,2,same)
Conv2D(64,3,2,same)+BN()+MaxPool2D(2,2,same)
Conv2D(128,3,2,same)+BN()+MaxPool2D(2,2,same)
Conv2D(256,3,2,same)+BN()+MaxPool2D(2,2,same)
ECA_block()
GlobalAvgpool2D()
Dense(8)
Optimizer of Discriminator0RMSprop(0.0002,0.5)
Optimizer of Discriminator1RMSprop(0.0002,0.5)
Optimizer of Discriminator2RMSprop(0.0002,0.5)
Optimizer of GeneratorRMSprop(0.0002,0.5)
Optimizer of ClassifierAdam(0.00002,0.5)
Table 1 Structure of MDACGAN model
标签故障类型
012k_Drive_End_B007_0
112k_Drive_End_B021_1
212k_Drive_End_IR007_0
312k_Drive_End_IR021_1
412k_Drive_End_OR007@3_0
512k_Drive_End_OR007@6_0
612k_Drive_End_OR007@12_0
712k_Drive_End_OR021@3_1
Table 2 Data labels and their fault types of experiment 1
Fig.3 Gray scale of partial fault data in experiment 1
Fig.4 Samples generated by different models on CWRU bearing fault data set
模型类别
01234567
ACGAN532.10532.11532.10532.11532.01532.10532.11532.11
ACWGAN-GP179.08326.34488.76171.87236.83199.66220.80532.00
MDACGAN34.3179.47220.2562.2868.2082.7188.68147.58
Table 3 DFI values between real samples and generated samples of CWRU bearing fault data set
模型类别
01234567
ACGAN4.330 54.873 74.661 95.337 84.445 54.761 75.637 85.071 2
ACWGAN-GP0.340 60.412 00.419 70.343 70.702 40.352 20.603 90.635 6
MDACGAN0.149 00.145 60.152 30.153 20.112 40.146 30.155 30.155 7
Table 4 DMM values between real samples and generated samples of CWRU bearing fault data set
Fig.5 Generated samples and training samples t-SNE visualization results of CWRU bearing fault data set
类型数据集样本总数/个①
测试集数据集0100
训练集数据集150（0）
数据集2100（50）
数据集3150（100）
数据集4200（150）
数据集5250（200）
数据集6350（300）
数据集7200（0）
Table 5 Expansion and division of CWRU bearing fault data set
模型准确率/%
数据集1数据集2数据集3数据集4数据集5数据集6数据集7
ACWGAN-GP78.3789.3792.6291.1293.8594.8799.75
MDACGAN78.3790.2593.7595.6297.1398.0099.75
Table 6 Classification result of CWRU bearing fault data set
标签工况故障类型失效位置
01Bearing1_1外圈
1Bearing1_4保持架
22Bearing2_1内圈
3Bearing2_2外圈
43Bearing3_3内圈
5Bearing3_5外圈
Table 7 Data labels and their fault types of experiment 2
Fig.6 Samples generated by different models on XJTU-SY data set
模型类别
012345
ACWGAN-GP270.87223.04220.8469.56116.89111.72
MDACGAN141.37178.31144.8760.16110.6566.07
Table 8 DFI values between real samples and generated samples of XJTU-SY data set
模型类别
012345
ACWGAN-GP0.233 80.352 90.310 90.239 00.339 30.213 3
MDACGAN0.164 80.198 20.160 20.115 00.178 90.122 8
Table 9 DMM values between real samples and generated samples of XJTU-SY data set
Fig.7 Generated samples and training samples t-SNE visualization results of XJTU-SY data set
模型准确率/%
数据集1数据集2数据集3数据集4数据集5数据集6数据集7
ACWGAN-GP75.0083.1683.5087.3390.1292.1699.66
MDACGAN75.0085.8688.2189.6691.8395.5099.66
Table 10 Classification result of XJTU-SY data set
标签试验序号测试的轴承失效位置
01轴承3内圈
1轴承4滚动体
22轴承1外圈
3轴承2—
43轴承1—
5轴承3外圈
6轴承4—
Table 11 Data labels and their fault types of experiment 3
Fig.8 Samples generated by different models on IMS data set
模型类别
0123456
ACWGAN-GP255.29148.21515.00195.62173.14237.86106.51
MDACGAN120.0023.40337.67141.6188.0190.9277.35
Table 12 DFI values between real samples and generated samples of IMS data set
模型类别
0123456
ACWGAN-GP0.366 80.323 60.321 60.344 20.311 20.332 40.324 5
MDACGAN0.180 50.141 50.213 30.134 20.144 30.197 00.116 3
Table 13 DMM values between real samples and generated samples of IMS data set
Fig.9 Generated samples and training samples t-SNE visualization results of IMS data set
模型准确率/%
数据集1数据集2数据集3数据集4数据集5数据集6数据集7
ACWGAN-GP75.2886.8588.7191.0089.0191.8597.28
MDACGAN75.2886.7188.8592.7193.1495.5797.28
Table14 Classification result of IMS data set
[1]   ZHONG J， HUANG Y. Time-frequency representation based on an adaptive short-time Fourier transform［J］. IEEE Transactions on Signal Processing， 2010， 58（10）： 5118-5128.
[2]   TSE P W， PENG Y H， YAM R. Wavelet analysis and envelope detection for rolling element bearing fault diagnosis： Their effectiveness and flexibilities ［J］. Journal of Vibration and Acoustics， 2001， 123（3）： 303-310.
[3]   HUANG N E， SHEN Z， LONG S R， et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］. Proceedings of the Royal Society of London Series A： Mathematical， Physical and Engineering Sciences， 1998， 454： 903-995.
[4]   DRAGOMIRETSKIY K， ZOSSO D. Variational mode decomposition［J］. IEEE Transactions on Signal Processing， 2013， 62（3）： 531-544.
[5]   ZHANG W， ZHANG F， CHEN W， et al. Fault state recognition of rolling bearing based fully convolutional network［J］. Computing in Science & Engineering， 2019， 21（5）： 55-63.
[6]   WANG D， GUO Q， SONG Y， et al. Application of multiscale learning neural network based on CNN in bearing fault diagnosis［J］. Journal of Signal Processing Systems， 2019， 91（10）： 1205-1217.
[7]   HE M， HE D. Deep learning based approach for bearing fault diagnosis［J］. IEEE Transactions on Industry Applications， 2017， 53（3）： 3057-3065.
[8]   RUAN D， SONG X， GÜHMANN C， et al. Collaborative optimization of CNN and GAN for bearing fault diagnosis under unbalanced datasets［J/OL］. Lubricants， 2021， 9（10）： 105［2023-10-20］. .
[9]   XIAO D， HUANG Y， QIN C， et al. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis［J］. Proceedings of the Institution of Mechanical Engineers Part C： Journal of Mechanical Engineering Science， 2019， 233（14）： 5131-5143.
[10]   崔旭浩，郗欣甫，孙以泽.数据驱动的经编机横移机构故障检测方法研究［J］.工程设计学报，2022，29（3）：263-271. doi：10.3785/j.issn.1006-754X.2022.00.030
CUI X H， XI X F， SUN Y Z. Research on data-driven fault detection method of traverse mechanism of warp knitting machine［J］. Chinese Journal of Engineering Design， 2022， 29 （3）： 263-271.
doi: 10.3785/j.issn.1006-754X.2022.00.030
[11]   REN S， ZHU W， LIAO B， et al. Selection-based resampling ensemble algorithm for nonstationary imbalanced stream data learning［J］. Knowledge-Based Systems， 2019， 163： 705-722.
[12]   陈保家，陈学力，肖文荣，等.小样本下滚动轴承故障的多源域迁移诊断方法［J］.电子测量与仪器学报，2022， 36（2）： 219-228.
CHEN J B， CHEN X L， XIAO W R， et al. Multi-source domain transfer diagnosis method for rolling bearing faults under small samples［J］. Journal of Electronic Measurement and Instrumentation， 2022， 36（2）： 219-228.
[13]   吴定会，方钦，吴楚宜.基于数据生成与迁移学习的轴承小样本故障诊断［J］.机械传动，2020，44（11）：139-144.
WU D H， FANG Q， WU C Y. Bearing small sample fault diagnosis based on data generation and transfer learning ［J］. Journal of Mechanical Transmission， 2020， 44（11）： 139-144.
[14]   GOODFELLOW I， POUGET-ABADIE J， MIRZA M， et al. Generative adversarial nets［C］//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal， Canada： MIT Press， 2014： 2672-2680.
[15]   GAO X， DENG F， YUE X. Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty［J］. Neurocomputing， 2020， 396： 487-494.
[16]   HAN T， LIU C， YANG W， et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults［J］. Knowledge-Based Systems， 2019， 165： 474-487.
[17]   ZHOU F， YANG S， FUJITA H， et al. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data［J］. Knowledge-Based Systems， 2020， 187： 104837.
[18]   LIU S， CHEN J， QU C， et al. LOSGAN： Latent optimized stable GAN for intelligent fault diagnosis with limited data in rotating machinery［J］. Measurement Science and Technology， 2021， 32（4）： 045101.
[19]   ODENA A， OLAH C， SHLENS J. Conditional image synthesis with auxiliary classifier GANS［EB/OL］. ［2023-10-20］. .
[20]   SHAO S， WANG P， YAN R. Generative adversarial networks for data augmentation in machine fault diagnosis ［J］. Computers in Industry， 2019， 106： 85-93.
[21]   卢锦玲，张祥国，张伟，等.基于改进辅助分类生成对抗网络的风机主轴承故障诊断［J］.电力系统自动化，2021， 45（7）：148-154. doi：10.7500/AEPS20200415002
LU J L， ZHANG X G， ZHANG W， et al. Fault diagnosis of main bearing of wind turbine based on improved auxiliary classifier generative adversarial network［J］. Automation of Electric Power System， 2021， 45（7）： 148-154.
doi: 10.7500/AEPS20200415002
[22]   HUANG N， CHEN Q， CAI G， et al. Fault diagnosis of bearing in wind turbine gearbox under actual operating conditions driven by limited data with noise labels［J］. IEEE Transactions on Instrumentation and Measurement， 2021， 70： 1-10.
[23]   何强，唐向红，李传江，等.负载不平衡下小样本数据的轴承故障诊断［J］.中国机械工程，2021，32（10）：1164-1171. doi：10.3969/j.issn.1004-132X.2021.10.004
HE Q， TANG X H， LI C J， et al. Bearing fault diagnosis method based on small sample data under unbalanced loads［J］. China Mechanical Engineering， 2021， 32（10）： 1164-1171.
doi: 10.3969/j.issn.1004-132X.2021.10.004
[24]   YANG Z K， BU L P， WANG T， et al. Fire image generation based on ACGAN［C］//The 31th Chinese Control and Decision Conference， Nanchang， Jiangxi， Jun.， 3-5， 2019.
[25]   DHARANYA V， JOSEPH RAJ A N， GOPI V P. Facial expression recognition through person-wise regeneration of expressions using auxiliary classifier generative adversarial network （AC-GAN） based model［J］. Journal of Visual Communication and Image Representation， 2021， 77： 103110.
[26]   LI W， ZHONG X， SHAO H， et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework［J］. Advanced Engineering Informatics， 2022， 52： 101552.
[27]   ARJOVSKY M， CHINTALA S， BOTTOU L. Wasserstein generative adversarial networks［C］//34th International Conference on Machine Learning， Sydney， Australia， Aug. 6-11， 2017.
[28]   王正龙，张保稳.生成对抗网络研究综述［J］.网络与信息安全学报，2021，7（4）：68-85. doi：10.11959/j.issn.2096-109x.2021080
WANG Z L， ZHANG B W. A survey of research on generative adversarial network［J］. Chinese Journal of Network and Information Security， 2021， 7（4）： 68-85.
doi: 10.11959/j.issn.2096-109x.2021080
[29]   GULRAJANI I， AHMED F， ARJOVSKY M， et al. Improved training of Wasserstein GANS［EB/OL］. ［2023-10-20］. .
[30]   MIRZA M， OSINDERO S. Conditional generative adversarial nets［J］. Computer Science， 2014： 2672-2680.
[31]   ODENA A. Semi-supervised learning with generative adversarial networks［EB/OL］. ［2023-10-20］. .
[32]   MORDIDO G， YANG H， MEINEL C. Dropout-GAN： Learning from a dynamic ensemble of discriminators［J］. arXiv preprint arXiv：， 2018.
[33]   WANG Q， WU B， ZHU P， et al. ECA-Net： Efficient channel attention for deep convolutional neural networks ［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition， Seattle， Washington， USA， Jun. 14-19. 2020.
[34]   PETZKA H， FISCHER A， LUKOVNICOV D. On the regularization of Wasserstein GANS［J］. arXiv preprint arXiv：， 2017.
[35]   SMITH W A， RANDALL 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.
[36]   WEN L， LI X， GAO L， et al. A new convolutional neural network-based data-driven fault diagnosis method［J］. IEEE Transactions on Industrial Electronics， 2018， 65（7）： 5990-5998.
[37]   HEUSEL M， RAMSAUER H， UNTERTHINER T， et al. GANS trained by a two time-scale update rule converge to a local Nash equilibrium［C］//NIPS'17： Proceedings of the 31st International Conference on Neural Information Processing Systems， Long Beach， CA， USA， Dec. 4-9， 2017.
[38]   GRETTON A， BORGWARDT K M， RASCH M J， et al. A kernel two-sample test［J］. The Journal of Machine Learning Research， 2012， 13（1）： 723-773.
[39]   PEZZOTTI N， LELOEVELDT B P， VAN DER MAATEN L， et al. Approximated and user steerable tSNE for progressive visual analytics［J］. IEEE Transactions on Visualization and Computer Graphics， 2016， 23（7）： 1739-1752.
[40]   雷亚国，韩天宇，王彪，等.XJTU-SY滚动轴承加速寿命试验数据集解读［J］.机械工程学报，2019，55（16）：1-6. doi：10.3901/jme.2019.16.001
LEI Y G， HAN T Y， WANG B， et al. XJTU-SY rolling element bearing accelerated life test datasets： A tutorial ［J］. Journal of Mechanical Engineering， 2019， 55（16）： 1-6.
doi: 10.3901/jme.2019.16.001
[1] Chao JI,Liang WANG,Xiao-jing WANG,Xiao-bing LI,Wen CAO. Design of cable tunnel fault warning system based on MSSA-SVM[J]. Chinese Journal of Engineering Design, 2023, 30(1): 109-116.
[2] WU Guo-pei, YU Yin-quan, TU Wen-bing. Review of research on fault diagnosis of permanent magnet synchronous motor[J]. Chinese Journal of Engineering Design, 2021, 28(5): 548-558.
[3] SHANG Zhi-wu, ZHOU Shi-qi. Research on micropipetting technology based on image monitoring[J]. Chinese Journal of Engineering Design, 2021, 28(4): 495-503.
[4] NI Hong-qi, JIN Chi, FENG Fei. Development of fault diagnosis system for corrugated compensator[J]. Chinese Journal of Engineering Design, 2019, 26(3): 354-363.
[5] MA Tian-bing, WANG Xiao-dong, DU Fei, WANG Xin-quan. Fault diagnosis for rigid guide based on GA-SVM[J]. Chinese Journal of Engineering Design, 2019, 26(2): 170-176.
[6] HU Yi-yao, ZHU Bin, ZHANG Wei, HE Wei, SHEN Ping-sheng. Design and implementation of knowledge base building tool software[J]. Chinese Journal of Engineering Design, 2018, 25(4): 367-373.
[7] LI Xiao-huo, WENG Zheng-yang, QIANG Ya-sen, SHI Shang-wei, LI Yan. Fault diagnosis of hydraulic breaking hammer based on Fruit Fly Algorithm optimized fuzzy RBF neural network[J]. Chinese Journal of Engineering Design, 2015, 22(6): 540-545.
[8] LI Ling-Ling, JING Li-Ting, MA Dong-Juan, LI Zhi-Gang. Improved evidence theory and its application in fault diagnosis of power system[J]. Chinese Journal of Engineering Design, 2012, 19(6): 485-488.
[9] HAN Hai-tao,MA Hong-guang,HAN Kun,ZHENG Geng-le. Multitone stimulus signal design for identifying volterra frequency domain kernels[J]. Chinese Journal of Engineering Design, 2012, 19(2): 123-127.
[10] HAO Zhi-Yong, LIU Wei, XIA Wei, YAN Chuang. Fault diagnosis of the fan with air suction based on BP neural network[J]. Chinese Journal of Engineering Design, 2012, 19(1): 57-60.
[11] HAN Hai-Tao, MA Hong-Guang, LI Fei, ZHANG Jia-Liang-. Research on nonlinear system based on output frequency response functions[J]. Chinese Journal of Engineering Design, 2011, 18(5): 373-376.
[12] GUO Yu-Xiu, NI Xiao-Hong, WANG Yu-Tian. Study on the fault diagnosis of rolling mills based
on the chaos weak signal detection method[J]. Chinese Journal of Engineering Design, 2011, 18(3): 218-221.
[13] WANG Cheng-Gang, WANG Xue-Wei, YANG Zhi-Yong, ZENG Ru-Wei. Study on correlation algorithm of failure mode rates in testability modeling[J]. Chinese Journal of Engineering Design, 2009, 16(4): 252-255.
[14] WANG Zi-Ling, XU Ai-Qiang, NIU Shuang-Cheng. Research and application on multiple fault diagnosis strategy[J]. Chinese Journal of Engineering Design, 2009, 16(4): 281-286.
[15] CHEN Yong, LIANG Jun. Slide—m odel M PCA approach with applications in fault detecting of m ultiVariable nonlinear process[J]. Chinese Journal of Engineering Design, 2003, 10(3): 131-135.