|Table of Contents|

Fault diagnosis method based on joint mean discrepancy matching for domain adaptation

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2020年03期
Page:
340-347
Research Field:
Publishing date:

Info

Title:
Fault diagnosis method based on joint mean discrepancy matching for domain adaptation
Author(s):
Dang GangYan GaoweiYan FeiChen Zehua
College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China
Keywords:
mean discrepancy domain adaptation fault diagnosis maximum variance source domain target domain
PACS:
TP29
DOI:
10.14177/j.cnki.32-1397n.2020.44.03.012
Abstract:
In view of the problem that the model data distribution is mismatched due to the sudden change of working conditions in the process of industrial fault diagnosis,a fault diagnosis method for industrial process based on joint mean discrepancy matching for domain adaptation is proposed. The intra class and inter class differences are defined by means of the mean values of each sample in the source domain and the target domain. The maximum variance and the maximum mean difference are integrated to obtain the feature projection matrix,and the feature information in the source modeling domain and the target modeling domain is projected into the common subspace. The K-nearest neighbor(KNN)classification model is established in the subspace to complete the fault diagnosis classification. The experimental results show that the method proposed here can complete the fault classification accurately,and has higher classification accuracy and flexibility.

References:

[1] 王征,高炜欣,陈义,等. 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(4):472-478.
Wang Zheng,Gao Weixin,Chen Yi,et al. Decoupling and suboptimal design of fault detection vectors in control systems[J]. Journal of Nanjing University of Science and Technology,2017,41(4):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(2):161-171.
Zhou Donghua,Shi Jiantao,He Xiao. Overview of intermittent fault diagnosis technology for dynamic systems[J]. Journal of Automation,2014,40(2):161-171.
[3]徐莹,邓晓刚,钟娜. 基于ICA混合模型的多工况过程故障诊断方法[J]. 化工学报,2016,67(9):3793-3803.
Xu Ying,Deng Xiaogang,Zhong Na. Fault diagnosis method of multi condition process based on ICA hybrid model[J]. Journal of Chemical Engineering,2016,67(9):3793-3803.
[4]Jiang Qingchao,Yan Xuefeng. Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA[J]. Journal of Process Control,2015,32(4):38-50.
[5]Yu Jie. 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.
[6]Ma Hehe,Hu Yi,Shi Hongbo. A novel local neighborhood standardization strategy and its application in fault detection of multimode processes[J]. Cemom Intell Lab Syst,2012,118(5):287-300
[7]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(6):134-141.
Guo Hongjie,Xu Chunling,Shi Hongbo. Fault detection of multi condition process based on local neighborhood standardization strategy[J]. Journal of Shanghai Jiaotong University,2015,49(6):134-141.
[8]石怀涛,刘建昌,张羽,等. 基于相对变换PLS的故障检测方法[J]. 仪器仪表学报,2012,33(4):816-822.
Shi Huaitao,Liu Jianchang,Zhang Yu,et al. Fault detection method based on relative transformation PLS[J]. Journal of Instrumentation,2012,33(4):816-822.
[9]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]. Journal of Chemical Engineering,2014,65(12):4866-4874
[10]Long Mingsheng,Wang Jianmin,Ding Guiguang,et al. Transfer feature learning with joint distribution adaptation[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney,Australia:IEEE,2013:2200-2207.
[11]Long Mingsheng,Wang Jianmin,Ding Guiguang,et al. Transfer joint matching for unsupervised domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Columbus,USA:IEEE Computer Society,2014:1410-1417.
[12]Al Hage J,Maan E E N,Pomorski D. Multi-sensor fusion approach with fault detection and exclusion based on the Kullback-Leibler divergence:Application on collaborative multi-robot system[J]. Information Fusion,2017,37(11):61-76.
[13]Wang Xiaogang,Jie Ren,Liu Sen. Distribution adaptation and manifold alignment for complex processes fault diagnosis[J]. Knowledge-Based Systems,2018,156(9):100-112.
[14]Pan S J,Tsang,Kwok I W,et al. Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Networks,2011,22(2):199-210.
[15]Lu Hao,Shen Chunhua,Cao Zhiguo,et al. An embarrassingly simple approach to visual domain adaptation[J]. IEEE Transactions on Image Processing,2018,27(7):3403-3417.
[16]Sun Qian,Chattopadhyay R,Panchanathan S,et al. A two-stage weighting framework for multi-source domain adaptation[C]//International Conference on Neural Information Processing Systems. New York,USA:Curran Associates Inc,2011:505-513.
[17]杜永贵,李思思,阎高伟,等. 基于流形正则化域适应湿式球磨机负荷参数软测量[J]. 化工学报,2018,69(3):1244-1251.
Du Yonggui,Li Sisi,Yan Gaowei,et al. Soft measurement of load parameters of wet ball mill based on manifold regularization domain[J]. Journal of Chemical Engineering,2018,69(3):1244-1251.
[18]Ricker N L. Decentralized control of the Tennessee Eastman challenge process[J]. Journal of Process Control,1996,6(4):205-221.
[19]Zhang Jing,Li Wanqing,Ogunbona P. Joint geometrical and statistical alignment for visual domain adaptation[C]//Proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,USA:IEEE,2017:5150-5158.

Memo

Memo:
-
Last Update: 2020-06-30