基于区分性联合概率分布的域适应故障诊断

摘要
图/表
参考文献(36)
相关文章 (15)

全文: PDF (2659 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对多工况条件下的故障诊断方法因建模数据和待测数据不满足独立同分布假设，导致模型性能恶化这一问题，提出了一种基于区分性联合概率分布差异的域适应故障诊断建模方法。首先，以一个结构风险最小化域不变分类器作为故障诊断框架。然后，在框架上施加基于区分性联合概率分布差异的域适应项，将建模数据和待测数据投影到公共特征空间中，对齐跨域同类别样本分布的同时，最大化跨域不同类别样本间分布差异；并且利用流形正则化保持数据的局部几何结构。最后，在多工况条件下的凯斯西储大学（CWRU）和帕德伯恩大学（PU）轴承故障诊断数据集上进行实验。实验结果表明本方法有效的提高故障诊断模型预测精度和泛化性，在多工况故障诊断任务中的表现良好。

	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
	周长巍1
	李国勇1
	任密蜂1
	叶泽甫2
	阎高伟1

关键词 ：故障诊断, 多工况, 迁移学习, 区分性域适应, 流形正则化

Abstract：Aiming at the problem that deterioration of fault diagnosis under multi-working condition caused by the training data and test data do not satisfy the assumption of independent and identical distribution. A discriminative joint probability based domain adaption for fault diagnosis was proposed. Firstly, a domain-invariant classifier with structural risk minimization is used as modeling framework. Then, a domain adaptation term based on the discriminative joint probability distribution difference is imposed on the framework. The term projects data into a common feature space, aligns the distribution of samples of the same category across domains, and maximizes the distribution differences between samples of different categories across domains. At the same time, the manifold regularization is used to preserve the local geometry of the data. Finally, the method was applied in the bearing fault diagnosis datasets of Case Western Reserve University (CWRU) and Paderborn University (PU). It was shown that the proposed method can effectively improve the prediction accuracy and generalization of the fault diagnosis model under multi-working condition.

Key words： fault diagnosis multi-working condition transfer learning discriminative domain adaptation manifold regularization

收稿日期: 2022-03-17 出版日期: 2023-04-15

引用本文:

周长巍1，李国勇1，任密蜂1，叶泽甫2，阎高伟1. 基于区分性联合概率分布的域适应故障诊断[J]. 振动与冲击, 2023, 42(7): 170-179.
ZHOU Changwei1, LI Guoyong1, REN Mifeng1, YE Zefu2, YAN Gaowei1. Domain adaption fault diagnosis based on discriminative joint probability distribution difference. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(7): 170-179.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I7/170

[1] 王征,高炜欣,陈义, et al.控制系统中故障检测向量的解耦及次优设计[J].南京理工大学学报,2017,41(04):472-478.
Wang Zheng, Gao Weixin, Chen Yi, et al.Decoupling and sub-optimal design of fault detection vector for control system[J]. Journal of Nanjing University of Science and Technology, 2017,41(04):472-478.
[2] 周东华,史建涛,何潇.动态系统间歇故障诊断技术综述[J].自动化学报,2014,40(02):161-171.
Zhou Donghua, Shi Jiantao, He Xiao. Review of Intermittent Fault Diagnosis Techniques for Dynamic Systems[J]. Acta Automatica Sinica,2014,40(02):161-171.
[3] Hoang D T, Kang H J. A survey on deep learning based bearing fault diagnosis[J]. Neurocomputing, 2019, 335: 327-335.
[4] Abdeljaber O, Avci O, Kiranyaz M S, et al. 1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data[J]. Neurocomputing, 2018, 275: 1308-1317.
[5] 赵光权,葛强强,刘小勇,et al.基于DBN的故障特征提取及诊断方法研究[J].仪器仪表学报,2016,37(09):1946-1953.
Zhao Guangquan, Ge Qiangqiang, Liu Xiaoyong, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument,2016, 37(09):1946-1953.
[6] 李恒,张氢,秦仙蓉, et al.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 Heng, Zhang Qin, Qin Xianrong, 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.
[7] Li X, Hu Y, Zheng J, et al. Central moment discrepancy based domain adaptation for intelligent bearing fault diagnosis[J]. Neurocomputing, 2021, 429: 12-24.
[8] Yu J. A new fault diagnosis method of multimode processes using Bayesian inference based Gaussian mixture contribution decomposition[J]. Engineering Applications of Artificial Intelligence, 2013, 26(1): 456-466.
[9] 郭红杰,徐春玲,侍洪波.基于局部邻域标准化策略的多工况过程故障检测[J].上海交通大学学报,2015,49(06):868-875+883.
Guo Hongjie, Xu chunling, Si Hongbo. Multimode Process Monitoring Based on Local Neighborhood Standardization Strategy[J]. Journal of Shanghai Jiaotong University,2015, 49(06):868-875+883.
[10] Ma H, Hu Y, Shi H. A novel local neighborhood standardization strategy and its application in fault detection of multimode processes[J]. Chemometrics and Intelligent Laboratory Systems, 2012, 118:287-300.
[11] 卢春红,熊伟丽,顾晓峰.基于贝叶斯推理的PKPCAM的非线性多模态过程故障检测与诊断方法[J].化工学报,2014,65(12):4866-4874.
Lu Chunhong, Xiong Weili, Gu Xiaofeng.Fault detection and diagnosis for nonlinear and multimode processes using Bayesian inference based PKPCAM approach[J]. CIESC Journal,2014,65(12):4866-4874.
[12] Pan S J, Tsang I W, Kwok J T, et al. Domain adaptation via transfer component analysis[J]. IEEE transactions on neural networks, 2010, 22(2): 199-210.
[13] Long M, Wang J, Ding G, et al. Transfer joint matching for unsupervised domain adaptation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 1410-1417.
[14] Wang J, Feng W, Chen Y, et al. Visual domain adaptation with manifold embedded distribution alignment[C]//Proceedings of the 26th ACM international conference on Multimedia. 2018: 402-410.
[15] Du Z, Yang B, Lei Y, et al. A hybrid transfer learning method for fault diagnosis of machinery under variable operating conditions[C]//2019 Prognostics and System Health Management Conference (PHM-Qingdao). IEEE, 2019: 1-5.
[16] Li W, Gu S, Zhang X, et al. Transfer learning for process fault diagnosis: Knowledge transfer from simulation to physical processes[J]. Computers & Chemical Engineering, 2020, 139: 106904.
[17] Zhanga B, Lia W, Tonga Z, et al. Bearing fault diagnosis under varying working condition based on domain adaptation[C]// the 25th International Congress on Sound and Vibration (ICSV25). 2018:23-27.
[18] Zhang Z, Chen H, Li S, et al. A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition[J]. Neurocomputing, 2020, 376: 54-64.
[19] Wang X, Ren J, Liu S. Distribution adaptation and manifold alignment for complex processes fault diagnosis[J]. Knowledge-Based Systems, 2018, 156: 100-112.
[20] Liang J, He R, Sun Z, et al. Aggregating randomized clustering-promoting invariant projections for domain adaptation[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(5): 1027-1042.
[21] Lu H, Shen C, Cao Z, et al. An embarrassingly simple approach to visual domain adaptation[J]. IEEE Transactions on Image Processing, 2018, 27(7):3403-3417.
[22] Xu Y, Fang X, Wu J, et al. Discriminative transfer subspace learning via low-rank and sparse representation[J]. IEEE Transactions on Image Processing, 2015, 25(2):850-863.
[23] Yang L, Zhong P. Discriminative and informative joint distribution adaptation for unsupervised domain adaptation[J]. Knowledge-Based Systems, 2020, 207:106394.
[24] Zhang W, Wu D. Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation[C]//2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020: 1-8.
[25] 雷亚国,杨彬,杜兆钧,et al.大数据下机械装备故障的深度迁移诊断方法[J].机械工程学报,2019,55(07):1-8.
Lei Yaguo, Yang Bin, Du Zhaojun, et al. Deep Transfer Diagnosis Method for Machinery in Big Data Era[J]. Journal of Mechanical Engineering, 2019,55(07):1-8.
[26] 李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策,2011,26(01):1-9+16.
Li Han, Xiao Deyun. Survey on data driven fault diagnosis methods[J]. Control and Decision,2011,26(01):1-9+16.
[27] 郭小萍,刘诗洋,李元.基于稀疏残差距离的多工况过程故障检测方法研究[J].自动化学报,2019,45(03):617-625.
Guo Xiaoping, Liu Shiyang, Li Yuan. Fault Detection of Multi-moda Processes Employing Sparse Residual Distance[J]. Acta Automatica Sinica,2019,45(03):617-625.
[28] Sanodiya R K , Yao L . Discriminative information preservation: A general framework for unsupervised visual Domain Adaptation[J]. Knowledge-Based Systems, 2021, 227(4):107158.
[29] Belkin M, Niyogi P, Sindhwani V. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples[J]. Journal of machine learning research, 2006, 7(11):2399-2434.
[30] Ben-David S, Blitzer J, Crammer K, et al. Analysis of representations for domain adaptation[J]. Advances in neural information processing systems, 2006, 19:137-144.
[31] Belkin M , Niyogi P , Sindhwani V . Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples[J]. Journal of Machine Learning Research, 2006, 7(1):2399-2434.
[32] Boudiaf A , Moussaoui A , Dahane A , et al. A Comparative Study of Various Methods of Bearing Faults Diagnosis Using the Case Western Reserve University Data[J]. Journal of Failure Analysis and Prevention, 2016, 16(2):271-284.
[33] Lessmeier C, Kimotho J K, Zimmer D, et al. Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification[C]//PHM Society European Conference. 2016, 3(1):5-8.
[34] Li X, Hu Y, Zheng J, et al. Central moment discrepancy based domain adaptation for intelligent bearing fault diagnosis[J]. Neurocomputing, 2021, 429:12-24.
[35] Baochen Sun, Jiashi Feng, Kate Saenko. Saenko K. Return of frustratingly easy domain adaptation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2016, 30(1):2058-2065.
[36] Wang J , Chen Y, Hao S, et al. Balanced distribution adaptation for transfer learning[C]//2017 IEEE international conference on data mining (ICDM). IEEE, 2017:1129-1134.