|Table of Contents|

Multi-block fault monitoring based on PCA method withhierarchical information extraction(PDF)

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

Issue:
2020年04期
Page:
471-480
Research Field:
Publishing date:

Info

Title:
Multi-block fault monitoring based on PCA method withhierarchical information extraction
Author(s):
Zhai Chao; Xiong Weili
School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China
Keywords:
hierarchical information extraction;  mutual information;  principal component analysis;  fault monitoring;  multi-block modelling
PACS:
TP277
DOI:
10.14177/j.cnki.32-1397n.2020.44.04.012
Abstract:
The traditional multi-block fault monitoring methods only use local information of the process,and other valid information of the data set is ignored. In view of this problem,a multi-block principal component analysis(PCA)fault monitoring method with hierarchical information extraction is proposed. Firstly,this paper calculates the mutual information between the process variables and blocks the process variables to extract the process local information. Second,this paper further digs the feature information of the process data,extracts the cumulative error and second-order difference information for each variable block,and with the observed values information expands each variable block into three information sub-blocks. Each sub-block is monitored by the PCA method,and the monitoring results of all the sub-blocks are integrated based on the Bayesian method. The validity and performance of the proposed method are verified and analyzed in Tennessee-Eastman(TE)process monitoring.

References:

[1] Qin S J. Statistical process monitoring:basics and beyond[J]. Journal of Chemometrics,2003,17(8/9):480-502.
[2]Ge Z Q,Song Z H,Gao F R. Review of recent research on data-based process monitoring[J]. Industrial & Engineering Chemistry Research,2013,52(10):3543-3562.
[3]Qin S J. Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control,2012,36(2):220-234.
[4]杜海莲,苗诗瑜,杜文霞,等. 改进主元分析方法及数据重构在工业系统中的故障诊断研究[J]. 南京理工大学学报,2019,43(1):72-77,85.
Du Hailian,Miao Shiyu,Du Wenxia,et al. Research on fault diagnosis of industrial systems based on improved principal component analysis method and data reconstruction[J]. Journal of Nanjing University of Science and Technology,2019,43(1):72-77,85.
[5]Liu Y,Liang Y,Gao Z,et al. Online flooding supervision in packed towers:an integrated data-driven statistical monitoring method[J]. Chemical Engineering & Technology,2018,41(3):436-446.
[6]Nguyen V H,Golinval J C. Fault detection based on kernel principal component analysis[J]. Journal of Central South University,2010,32(11):3683-3691.
[7]Ge Z Q,Song Z H. Process monitoring based on independent component analysis-principal component analysis(ICA-PCA)and similarity factors[J]. Industrial & Engineering Chemistry Research,2007,46(7):2054-2063.
[8]Zhou D,Li G,Qin S J. Total projection to latent structures for process monitoring[J]. Aiche Journal,2010,56(1):168-178.
[9]郑皓,熊伟丽. 基于多阶段ICA-SVDD的间歇过程故障监测[J]. 南京理工大学学报,2018,42(2):195-203.
Zheng Hao,Xiong Weili. Fault monitoring of intermittent process based on multi-stage ICA-SVDD[J]. Journal of Nanjing University of Science and Technology,2018,42(2):195-203.
[10]Cherry G A,Qin S J. Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis[J]. IEEE Transactions on Semiconductor Manufacturing,2006,19(2):159-172.
[11]Multi-block methods in multivariate process control[J]. Journal of Chemometrics,2008,22(11/12):580-586.
[12]Macgregor J F. Process monitoring and diagnosis by multiblock PLS methods[J]. AIChE J,1994,40(5):826-838.
[13]Westerhuis J A,Kourti T,MacGregor J F. Analysis of multiblock and hierarchical PCA and PLS models[J]. Journal of Chemometrics:A Journal of the Chemometrics Society,1998,12(5):301-321.
[14]Jiang Q C,Yan X F,Huang B. Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference[J]. IEEE Transactions on Industrial Electronics,2015,63(1):377-386.
[15]Huang J,Yan X. Dynamic process fault detection and diagnosis based on dynamic principal component analysis,dynamic independent component analysis and Bayesian inference[J]. Chemometrics and Intelligent Laboratory Systems,2015,148:115-127.
[16]顾炳斌,熊伟丽. 基于多块信息提取的PCA故障诊断方法[J]. 化工学报,2019,70(2):316-329.
Gu Bingbin,Xiong Weili. PCA fault diagnosis method based on multi-block information extraction[J]. CIESC Journal,2019,70(2):316-329.
[17]赵帅,宋冰,侍洪波. 基于加权互信息主元分析算法的质量相关故障检测[J]. 化工学报,2018,69(3):962-973.
Zhao Shuai,Song Bing,Shi Hongbo. Quality-related fault detection based on weighted mutual information principal component analysis algorithm[J]. CIESC Journal,2018,69(3):962-973.
[18]Li W. Mutual information functions versus correlation functions[J]. Journal of Statistical Physics,1990,60(5/6):823-837.
[19]Jiang Q,Yan X. Plant-wide process monitoring based on mutual information-multiblock principal component analysis[J]. ISA Transactions,2014,53(5):1516-1527.
[20]Ge Z Q,Chen J. Plant-wide industrial process monitoring:a distributed modeling framework[J]. IEEE Transactions on Industrial Informatics,2017,12(1):310-321.
[21]Shen Y,Ding S X,Haghani A,et al. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process[J]. Journal of Process Control,2012,22(9):1567-1581.
[22]Russell E L,Chiang L H,Braatz R D. Tennessee Eastman Process[C]//Fault Detection and Diagnosis in Industrial Systems. London:Springer,2001:103-112.

Memo

Memo:
-
Last Update: 2020-08-30