一种融合贝叶斯推理与LDRSKM的多模态过程监测算法

Ren Shi-jin; Liang Yin; Zhao Xiang-jun; Yang Mao-yun

doi:10.1631/FITEE.1400263

Your Location：

Home >

Browse articles >

一种融合贝叶斯推理与LDRSKM的多模态过程监测算法

计算机与自动化 | Updated：2022-06-14

- 一种融合贝叶斯推理与LDRSKM的多模态过程监测算法
  Enhanced Publication
- A novel multimode process monitoring method integrating LDRSKM with Bayesian inference*
- 信息与电子工程前沿（英文） 2015年16卷第8期页码：617-633
- Affiliations：
  
  1.National Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
  2.School of Computer Science & Technology, Jiangsu Normal University, Xuzhou 221116, China
- Author bio：
  
  †E-mail:sjren_phd@163.com
- Funds：
  
  *Project supported by the National Natural Science Foundation of China (No. 61272297)
- DOI：10.1631/FITEE.1400263
  中图分类号：
- 纸质出版日期：2015-08，
  
  收稿日期：2014-07-20，
  
  修回日期：2015-07-08，
  
  录用日期：2015-05-03
- Accepted：
Scan QR Code
一种融合贝叶斯推理与LDRSKM的多模态过程监测算法[J]. 信息与电子工程前沿（英文）, 2015,16(8):617-633.

REN SHI-JIN, LIANG YIN, ZHAO XIANG-JUN, et al. A novel multimode process monitoring method integrating LDRSKM with Bayesian inference*. [J]. Frontiers of information technology & electronic engineering, 2015, 16(8): 617-633.
一种融合贝叶斯推理与LDRSKM的多模态过程监测算法[J]. 信息与电子工程前沿（英文）, 2015,16(8):617-633. DOI： 10.1631/FITEE.1400263.

REN SHI-JIN, LIANG YIN, ZHAO XIANG-JUN, et al. A novel multimode process monitoring method integrating LDRSKM with Bayesian inference*. [J]. Frontiers of information technology & electronic engineering, 2015, 16(8): 617-633. DOI： 10.1631/FITEE.1400263.

摘要

目的

针对复杂多模态工业过程故障监测存在的问题，充分利用过程数据的局部和非局部几何信息，同时实现数据聚类和低维子空间选择，提高非线性、非高斯多模态过程监测性能。

创新点

提出融合局部鉴别正则化软

-均值与贝叶斯推理的多模态过程监测算法。该方法充分利用过程数据的局部和非局部几何信息，较好地发挥了无监督学习和有监督学习的优点，提高了模态数据的分离性和解释性，监测性能良好。

方法

该方法分为二个阶段：第一阶段，首先，考虑过程数据的局部和非局部几何信息，提出一种局部保持的正则化软

-均值聚类算法（LPRSKM）。然后，建立有监督学习与无监督学习的统一框架，提出融合LPRSKM与广义线性鉴别分析算法(GELDA)的局部鉴别正则化软

-均值算法(LDRSKM)(图1)。第二阶段，使用核支持向量数据描述(KSVDD)对各局部子空间建立监测统计量及控制限。然后，基于贝叶斯推理方法建立多模态过程全局监测统计量。最后，在TE仿真平台对所提方法进行仿真分析。

结论

针对非线性、非高斯的多模态过程监测，提出一种新的数据划分和最优低维子空间选择的迭代算法来提高不同模态数据的分离效果。在此基础上使用KSVDD和贝叶斯推理方法，较好地解决了多个非高斯和非线性的过程模态的监测准确性和可靠性问题。

Abstract

A local discriminant regularized soft

-means (LDRSKM) method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft

-means algorithm by exploiting the local and non-local geometric information of the data and generalized linear discriminant analysis to provide a better and more meaningful data partition. LDRSKM can perform clustering and subspace selection simultaneously

enhancing the separability of data residing in different clusters. With the data partition obtained

kernel support vector data description (KSVDD) is used to establish the monitoring statistics and control limits. Two Bayesian inference based global fault detection indicators are then developed using the local monitoring results associated with principal and residual subspaces. Based on clustering analysis

Bayesian inference and manifold learning methods

the within and cross-mode correlations

and local geometric information can be exploited to enhance monitoring performances for nonlinear and non-Gaussian processes. The effectiveness and efficiency of the proposed method are evaluated using the Tennessee Eastman benchmark process.

关键词

多模态过程监测局部鉴别正则化软k-均值核支持向量数据描述贝叶斯推理

Keywords

Multimode process monitoringLocal discriminant regularized soft k-means clusteringKernel support vector data descriptionBayesian inferenceTennessee Eastman process

references

LF Cai, XM Tian, N Zhang. A kernel time structure independent component analysis method for nonlinear process monitoring. Chin J Chem Eng, 2014. 22(11-12):1243-1253. DOI:10.1016/j.cjche.2014.09.021http://doi.org/10.1016/j.cjche.2014.09.021.

LH Chiang, EL Russell, RD Braatz. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis. Chemometr Intell Lab Syst, 2000. 50(2):243-252. DOI:10.1016/S0169-7439(99)00061-1http://doi.org/10.1016/S0169-7439(99)00061-1.

XG Deng, XM Tian. Sparse kernel locality preserving projection and its application in nonlinear process fault detection. Chin J Chem Eng, 2013. 21(2):163-170. DOI:10.1016/S1004-9541(13)60454-1http://doi.org/10.1016/S1004-9541(13)60454-1.

XG Deng, XM Tian, S Chen. Modified kernel principal component analysis based on local structure analysis and its application to nonlinear process fault diagnosis. Chemometr Intell Lab Syst, 2013. 127195-209. DOI:10.1016/j.chemolab.2013.07.001http://doi.org/10.1016/j.chemolab.2013.07.001.

WW Dong, Y Yao, FR Gao. Phase analysis and identification method for multiphase batch processes with partitioning multi-way principal component analysis (MPCA) model. Chin J Chem Eng, 2012. 20(6):1121-1127. DOI:10.1016/S1004-9541(12)60596-5http://doi.org/10.1016/S1004-9541(12)60596-5.

JJ Downs, EF Vogel. A plant-wide industrial process control problem. Comput Chem Eng, 1993. 17(3):245-255. DOI:10.1016/0098-1354(93)80018-Ihttp://doi.org/10.1016/0098-1354(93)80018-I.

T Feital, U Kruger, J Dutra, 等. Modeling and performance monitoring of multivariate multimodal processes. AIChE J, 2013. 59(5):1557-1569. DOI:10.1002/aic.13953http://doi.org/10.1002/aic.13953.

ZQ Ge, ZH Song. Maximum-likelihood mixture factor analysis model and its application for process monitoring. Chemometr Intell Lab Syst, 2010. 102(1):53-61. DOI:10.1016/j.chemolab.2010.04.002http://doi.org/10.1016/j.chemolab.2010.04.002.

ZQ Ge, ZH Song. A distribution-free method for process monitoring. Exp Syst Appl, 2012. 38(8):9812-9829. DOI:10.1016/j.eswa.2011.02.048http://doi.org/10.1016/j.eswa.2011.02.048.

ZQ Ge, MG Zhang, ZH Song. Nonlinear process monitoring based on linear subspace and Bayesian inference. J Process Contr, 2010. 20(5):676-688. DOI:10.1016/j.jprocont.2010.03.003http://doi.org/10.1016/j.jprocont.2010.03.003.

ZQ Ge, ZH Song, FR Gao. Review of recent research on data-based process monitoring. Ind Eng Chem Res, 2013. 52(10):3543-3562. DOI:10.1021/ie302069qhttp://doi.org/10.1021/ie302069q.

K Ghosh, M Ramteke, R Srinivasan. Optimal variable selection for effective statistical process monitoring. Comput Chem Eng, 2014. 60260-276. DOI:10.1016/j.compchemeng.2013.09.014http://doi.org/10.1016/j.compchemeng.2013.09.014.

XF He, D Cai, YL Shao, 等. Laplacian regularized Gaussian mixture model for data clustering. IEEE Trans Knowl Data Eng, 2011. 23(9):1406-1418. DOI:10.1109/TKDE.2010.259http://doi.org/10.1109/TKDE.2010.259.

P Howland, J Wang, H Park. Solving the small sample size problem in face recognition using generalized discriminant analysis. Patt Recog, 2006. 39(2):277-287. DOI:10.1016/j.patcog.2005.06.013http://doi.org/10.1016/j.patcog.2005.06.013.

LP Jing, MK Ng, JZ Huang. An entropy weighting k-means algorithm for subspace clustering of high- dimensional sparse data. IEEE Trans Knowl Data Eng, 2007. 19(8):1026-1041. DOI:10.1109/TKDE.2007.1048http://doi.org/10.1109/TKDE.2007.1048.

M Kano, K Nagao, S Hasebe, 等. Comparison of multivariate statistical process monitoring methods with applications to the Eastman challenge problem. Comput Chem Eng, 2002. 26(2):161-174. DOI:10.1016/S0098-1354(01)00738-4http://doi.org/10.1016/S0098-1354(01)00738-4.

M Kano, T Fujioka, O Tonomura, 等. Data-based and model-based blockage diagnosis for stacked microchemical processes. Chem Eng Sci, 2007. 62(4):1073-1080. DOI:10.1016/j.ces.2006.11.011http://doi.org/10.1016/j.ces.2006.11.011.

D Lee, J Lee. Domain described support vector classifier for multi-classification problems. Patt Recog, 2007. 40(1):41-51. DOI:10.1016/j.patcog.2006.06.008http://doi.org/10.1016/j.patcog.2006.06.008.

J Lee, B Kang, S Kang. Integrating independent component analysis and local outlier factor for plant-wide process monitoring. J Process Contr, 2011. 21(7):1011-1021. DOI:10.1016/j.jprocont.2011.06.004http://doi.org/10.1016/j.jprocont.2011.06.004.

JL Liu, D Cai, XF He. Gaussian mixture model with local consistency. 2010. Proc. 24th AAAI Conf. on Artificial Intelligence. 512-517. .

AM Miao, ZQ Ge, ZH Song, 等. Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection. Chemometr Intell Lab Syst, 2015. 142184-196. DOI:10.1016/j.chemolab.2015.01.010http://doi.org/10.1016/j.chemolab.2015.01.010.

S Miyamoto, M Mukaidono. Fuzzy C-means as a regularization and maximum entropy approach. 1997. Proc. IFSA. 86-92. .

GD Molina, DAR Zumoffen, MS Basualdo. Plant-wide control strategy applied to the Tennessee Eastman process at two operating points. Comput Chem Eng, 2011. 35(10):2081-2097. DOI:10.1016/j.compchemeng.2010.11.006http://doi.org/10.1016/j.compchemeng.2010.11.006.

YS Ng, R Srinivasan. An adjoined multi-model approach for monitoring batch and transient operations. Comput Chem Eng, 2009. 33(4):887-902. DOI:10.1016/j.compchemeng.2008.11.014http://doi.org/10.1016/j.compchemeng.2008.11.014.

CFA Perez. Fault Diagnosis with Reconstruction- Based Contributions for Statistical Process Monitoring. PhD T, 2011. University of Southern California, USA, .

J Serradilla, JQ Shi, AJ Morris. Fault detection based on Gaussian process latent variable models. Chemometr Intell Lab Syst, 2011. 109(1):9-21. DOI:10.1016/j.chemolab.2011.07.003http://doi.org/10.1016/j.chemolab.2011.07.003.

JF Shen, JJ Bu, B Ju, 等. Refining Gaussian mixture model based on enhanced manifold learning. Neurocomputing, 2012. 8719-25. DOI:10.1016/j.neucom.2012.01.029http://doi.org/10.1016/j.neucom.2012.01.029.

B Song, YX Ma, HB Shi. Multimode process monitoring using improved dynamic neighborhood preserving embedding. Chemometr Intell Lab Syst, 2014. 13517-30. DOI:10.1016/j.chemolab.2014.03.013http://doi.org/10.1016/j.chemolab.2014.03.013.

SC Tan, CP Lim, MVC Rao. A hybrid neural network model for rule generation and its application to process fault detection and diagnosis. Eng Appl Artif Intell, 2007. 20(2):203-213. DOI:10.1016/j.engappai.2006.06.007http://doi.org/10.1016/j.engappai.2006.06.007.

P Teppola, SP Mujunen, P Minkkinen. Adaptive fuzzy C-means clustering in process monitoring. Chemometr Intell Lab Syst, 1999. 45(1-2):23-38. DOI:10.1016/S0169-7439(98)00087-2http://doi.org/10.1016/S0169-7439(98)00087-2.

CD Tong, A Palazoglu, XF Yan. An adaptive multimode process monitoring strategy based on mode clustering and mode unfolding. J Process Contr, 2013. 23(10):1497-1507. DOI:10.1016/j.jprocont.2013.09.017http://doi.org/10.1016/j.jprocont.2013.09.017.

V Venkatasubramanian, R Rengaswamy, K Yin, 等. A review of process fault detection and diagnosis: Part I: quantitative model-based methods. Comput Chem Eng, 2003. 27(3):293-311. DOI:10.1016/S0098-1354(02)00160-6http://doi.org/10.1016/S0098-1354(02)00160-6.

L Xie, XQ Liu, JM Zhang, 等. Non-Gaussian process monitoring based on NGPP-SVDD. Acta Autom Sin, 2009. 35(1):107-112. (in Chinese).

X Xie, HB Shi. Multimode process monitoring based on fuzzy C-means in locality preserving projection subspace. Chin J Chem Eng, 2012. 20(6):1174-1179. DOI:10.1016/S1004-9541(12)60604-1http://doi.org/10.1016/S1004-9541(12)60604-1.

X Xu, L Xie, S Wang. Multi-mode process monitoring method based on PCA mixture model. CIESC J, 2011. 62(3):743-752. (in Chinese).

YH Yang, X Li, XZ Liu, 等. Wavelet kernel entropy component analysis with application to industrial process monitoring. Neurocomputing, 2015. 147395-402. DOI:10.1016/j.neucom.2014.06.045http://doi.org/10.1016/j.neucom.2014.06.045.

XS Yin, SC Chen, EL Hu. Regularized soft K-means for discriminant analysis. Neurocomputing, 2013. 10329-42. DOI:10.1016/j.neucom.2012.08.021http://doi.org/10.1016/j.neucom.2012.08.021.

J Yu. A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes. Chem Eng Sci, 2012. 68(1):506-519. DOI:10.1016/j.ces.2011.10.011http://doi.org/10.1016/j.ces.2011.10.011.

X Zang, FP Vista Iv, KT Chong. Fast global kernel fuzzy c-means clustering algorithm for consonant/vowel segmentation of speech signal. J Zhejiang Univ-Sci C (Comput & Electron), 2014. 15(7):551-563. DOI:10.1631/jzus.C1300320http://doi.org/10.1631/jzus.C1300320.

M Zhang, ZQ Ge, ZH Song, 等. Global-local structure analysis model and its application for fault detection and identification. Ind Eng Chem Res, 2011. 50(11):6837-6848. DOI:10.1021/ie102564dhttp://doi.org/10.1021/ie102564d.

SJ Zhang, ZL Wang, F Qian. FS-SVDD based on LTSA and its application to chemical process monitoring. CIESC J, 2010. 61(8):1894-1900. (in Chinese).

YW Zhang. Enhanced statistical analysis of nonlinear processes using KPCA, KICA and SVM. Chem Eng Sci, 2009. 64(5):801-811. DOI:10.1016/j.ces.2008.10.012http://doi.org/10.1016/j.ces.2008.10.012.

YW Zhang, S Li. Modeling and monitoring of nonlinear multi-mode processes. Contr Eng Pract, 2014. 22194-204. DOI:10.1016/j.conengprac.2013.04.007http://doi.org/10.1016/j.conengprac.2013.04.007.

YW Zhang, JY An, ZM Li, 等. Modeling and monitoring for handling nonlinear dynamic processes. Inform Sci, 2013. 23597-105. DOI:10.1016/j.ins.2012.04.023http://doi.org/10.1016/j.ins.2012.04.023.

ZB Zhu, PL Wang, ZH Song. PCA-SVDD based fault detection and self-learning identification. J Zhejiang Univ (Eng Sci), 2010. 44(4):652-658. (in Chinese).

ZB Zhu, ZH Song, A Palazoglu. Process pattern construction and multi-mode monitoring. J Process Contr, 2012. 22(1):247-262. DOI:10.1016/j.jprocont.2011.08.002http://doi.org/10.1016/j.jprocont.2011.08.002.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据