基于点密度标签传播的工业过程故障分类

doi:10.3969/j.issn.2095-2198.2022.05.008

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

PDF (1418KB)
输出: BibTeX | EndNote (RIS)

摘要

在工业过程监控中，标记数据对于提高故障分类性能起到非常重要的作用.但由于对过程数据进行标记需要耗费大量的人力物力，因此很难获取大量的标记数据.针对标记数据有限性问题和故障分类问题，本文提出了基于点密度标签传播的数据标签预测方法和故障分类方法.首先，基于点密度的标签传播方法假设流形上的数据具有相似的结构，并且近邻的数据具有相似的标签，利用数据的分布特征和点密度，为初始标签矩阵给出新的定义，充分考虑未标记数据和历史数据之间的内在联系，将标签从标记数据传播给未标记数据；然后，提出了基于点密度标签传播-半监督费舍尔判别分析的故障分类方法；最后，以Toy数据集和青霉素发酵过程为例对本文所提出的方法进行验证，结果表明所提出的方法具有较好的标签预测性能和故障分类性能.

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	（）
	作者相关文章

关键词: 标签传播')" href="#">

标签传播点密度故障分类

Abstract:

In industrial process monitoring,labeled data plays a very important role in improving the performance of fault classification However,it is difficult to obtain a large amount of labeled data because it takes a lot of manpower and material resources to label the process data Aiming at the problem of limited labeled data and fault classification,label prediction method and fault classification method based on dot density label propagation (DDLP) is proposed Firstly,DDLP method assumes that the data on the manifold have similar structures,while the nearby data have similar labels Using the distribution characteristics and the dot density of the data,this method considers the internal relationship between unlabeled data and historical data,a new definition for the initial label matrix is given,which is significance to label propagation,and propagates labels from labeled data to unlabeled data Moreover,a fault classification method based on point density label propagation-semisupervised fisher discriminant analysis (DDLP-SFDA) is proposed Furthermore,taking the Toy data and penicillin fermentation process as example,the results show that the proposed method has good label prediction performance and fault classification performance.

Key words: label propagation')" href="#">

label propagation dot density fault classification

出版日期: 2022-10-30 发布日期: 2024-03-22 整期出版日期: 2022-10-30

ZTFLH:

TP277

基金资助:

辽宁省自然科学基金计划项目(2022-BS-211)；辽宁省教育厅基本科研项目（LJKMZ20220776）

作者简介: 谢莹（1986—），女，辽宁辽阳人，讲师，博士，主要从事基于数据的过程监控研究.

引用本文:

谢莹, 胡范超, 刘雪伟.

基于点密度标签传播的工业过程故障分类 [J]. 沈阳化工大学学报, 2022, 36(5): 438-445.
XIE Ying HU Fan-chao LIU Xue-wei.

Fault Classification Based on Dot Density Label Propagation for Industrial Processes . Journal of Shenyang University of Chemical Technology, 2022, 36(5): 438-445.

链接本文:

https://xuebao.syuct.edu.cn/CN/10.3969/j.issn.2095-2198.2022.05.008 或 https://xuebao.syuct.edu.cn/CN/Y2022/V36/I5/438

［1］YU J.Localized Fisher Discriminant Analysis Based Complex Chemical Process Monitoring［J］.AICHE Journal,2011,57(7):1817-1828.

［2］PAUDYAL S,ATIQUE M S A,YANG C X.Local Maximum Acceleration Based Rotating Machinery Fault Classification Using KNN［C］.Brookings:IEEE International Conference on Electro Information Technology,2019:219-224.

［3］李元,白岩松.改进主成分分析的KNN故障检测研究［J］.沈阳化工大学学报,2018,32(4):80-85.

［4］JAN S U,LEE Y,SHIN J,et al.Sensor Fault Classification Based on Support Vector Machine and Statistical Time-Domain Features［J］.IEEE Access,2017,5:8682-8690.

［5］GUO J,LI T,LI Y.SVM Based on Gaussian and Non-Gaussian Double Subspace for Fault Detection［J］.IEEE Access,2021,9:66519-66530.

［6］ABDELGAYED T S,MORSI W G,SIDHU T S.Fault Detection and Classification Based on Co-training of Semisupervised Machine Learning［J］.IEEE Transactions on Industrial Electronics,2018,65(2):1595-1605.

［7］CHEN S,CERDA F,RIZZO P,et al.Semi-supervised Multiresolution Classification Using Adaptive Graph Filtering with Application to Indirect Bridge Structural Health Monitoring［J］.IEEE Transactions on Signal Processing,2014,62(11):2879-2893.

［8］FENG J,WANG J,HAN Z.Process Monitoring for Chemical Process Based on Semi-Supervised Principal Component Analysis［C］.Guiyang:Chinese Control and Decision Conference,2013:4282-4286.

［9］YAN Z,HUANG C,YAO Y.Semi-supervised Mixture Discriminant Monitoring for Chemical Batch Processes［J］.Chemometrics and Intelligent Laboratory Systems,2014,134(5):10-22.

［10］ZHONG S,WEN Q,GE Z.Semi-supervised Fisher Discriminant Analysis Model for Fault Classification in Industrial Processes［J］.Chemometrics and Intelligent Laboratory Systems,2014,138:203-211.

［11］ZHOU D,BOUSQUET O,LAL T N,et al.Learning with Local and Global Consistency［C］.Neural Information Processing Systems,2003:321-328.

［12］ZHANG C,WANG S,LI D,et al.Prior Class Dissimilarity Based Linear Neighborhood Propagation［J］.Knowledge Based Systems,2015,83:58-65.

［13］WANG F,ZHANG C.Label Propagation through Linear Neighborhoods［J］.IEEE Transactions on Knowledge and Data Engineering,2008,20(1):55-67.

［14］NIE F,XIANG S,LIU Y,et al.A General Graph-based Semi-supervised Learning with Novel Class Discovery［J］.Neural Computing and Applications,2010,19(4):549-555.

［15］ZHANG Z,WANG L,JIA L,et al.Projective Label Propagation by Label Embedding:A Deep Label Prediction Framework for Representation and Classification［J］.Knowledge-Based Systems,2017,119:94-112.

［16］[JP3]JIA L,ZHANG Z,WANG L,et al.Adaptive Neighborhood Propagation by Joint L2,1-norm Regularized Sparse Coding for Representation and Classification［C］.Barcelona:2016 IEEE 16th International Conference on Data Mining (ICDM),2016:201-210.

［17］ZOIDI O,TEFAS A,NIKOLAIDIS N,et al.Positive and Negative Label Propagations［J］.IEEE Transactions on Circuits and Systems for Video Technology,2018,28(2):342-355.

［18］ZHANG Z,JIA L,ZHAO M,et al.Adaptive Non-negative Projective Semi-supervised Learning for Inductive Classification［J］.Neural Networks,2018,108:128-145.

［19］LIN G,LIAO K,SUN B,et al.Dynamic Graph Fusion Label Propagation for Semi-supervised Multi-[JP]modality Classification［J］.Pattern Recognition,2017,68:14-23.

［20］ZHAO Y,BALL R,MOSESIAN J,et al.Graph-based Semi-supervised Learning for Fault Detection and Classification in Solar Photovoltaic Arrays［J］.IEEE Transactions on Power Electronics,2015,30(5):2848-2858.

［21］XIE Y.Modified Label Propagation on Manifold with Applications to Fault Classification［J］.IEEE Access,2020,8:97771-97782.

［22］JIA L,ZHANG Z,JIANG W.Transductive Classification by Robust Linear Neighborhood Propagation［C］.Xian:Advances in Multimedia Information Processing,2016:296-305.

［23］NIE F,XU D,TSANG I W,et al.Flexible Manifold Embedding:A Framework for Semi-supervised and Unsupervised Dimension Reduction［J］.IEEE Transactions on Image Processing,2010,19(7):1921-1932.

［24］JIN X,YUAN F,CHOW T,et al.Weighted Local and Global Regressive Mapping:A New Manifold Learning Method for Machine Fault Classification［J］.Engineering Applications of Artificial Intelligence,2014,30:118-128.

［25］KOKIOPOULOU E,CHEN J,SAAD Y.Trace Optimization and Eigenproblems in Dimension Reduction Methods［J］.Numerical Linear Algebra with Applications,2011,18(3):565-602.

［26］CHIANG L H,RUSSELL E L,BRAATZ R D.Fault Diagnosis in Chemical Processes Using Fisher Discriminant Analysis,Discriminant Partial Least Squares,and Principal Component Analysis［J］.Chemometrics and Intelligent Laboratory Systems,2000,50(2):243-252.

［27］YAN H,ZHOU J,PANG C K.Gaussian Mixture Model Using Semisupervised Learning for Probabilistic Fault Diagnosis under New Data Categories［J］.IEEE Transactions on Instrumentation and Measurement,2017,66(4):723-733.

［28］YU J.A Nonlinear Kernel Gaussian Mixture Model Based Inferential Monitoring Approach for Fault [JP2]Detection and Diagnosis of Chemical Processes［J］.Chemical Engineering Science,2012,68(1):506-519.

［29］GE Z,GAO F,SONG Z.Mixture Probabilistic PCR Model for Soft Sensing of Multimode Processes［J］.Chemometrics and Intelligent Laboratory Systems,2011,105(1):91-105.

［30］NIE F,XIANG S,JIA Y,et al.Semi-supervised Orthogonal Discriminant Analysis via Label Propagation［J］.Pattern Recognition,2009,42(11):2615-2627.

［31］FENG J,LI K.MRS-kNN Fault Detection Method for Multirate Sampling Process Based Variable Grouping Threshold［J］.Journal of Process Control,2020,85:149-158.

［32］ZHANG S,ZHAO C,GAO F.Incipient Fault Detection for Multiphase Batch Processes with Limited Batches［J］.IEEE Transactions on Control Systems and Technology,2019,27(1):103-117.

［33］SUN R,ZHANG Y.Fault Diagnosis with Between Mode Similarity Analysis Reconstruction for Multimode Processes［J］.Chemometrics and Intelligent Laboratory Systems,2017,164:43-51.

［34］YU J.Multiway Discrete Hidden Markov Model-based Approach for Dynamic Batch Process Monitoring and Fault Classification［J］.AICHE Journal,2012,58(9):2714-2725.

[1]	李元, 杨东昇, 李大舟. 基于二维卷积神经网络高层数据特征学习的过程故障检测[J]. 沈阳化工大学学报, 2021, 35(3): 256-264.
[2]	郭金玉, 刘玉超, 李元. 加权局部近邻标准化PCA的工业过程故障检测 [J]. 沈阳化工大学学报, 2021, 35(3): 265-274.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed