Industrial process monitoring using nonlinear principal component models

被引：4

作者：

Antory, D ^{[1
]}

Kruger, U ^{[1
]}

Irwin, GW ^{[1
]}

McCullough, G ^{[1
]}

机构：

[1] QUB, Virtual Engn Ctr, Belfast BT9 5HN, Antrim, North Ireland

来源：

2004 2ND INTERNATIONAL IEEE CONFERENCE INTELLIGENT SYSTEMS, VOLS 1 AND 2, PROCEEDINGS | 2004年

关键词：

fault detection; kernel density estimation; multivariate statistical process control; nonlinear principal component analysis;

D O I：

10.1109/IS.2004.1344685

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new approach to identifying nonlinear principal component models is presented. This involves the application of linear principal component analysis (PCA) prior to the identification of a modified autoassociative neural network (AAN) that represents the required nonlinear PCA model. The benefits of this new approach are that (i) the size of the reduced set of linear principal components (PCs) is smaller than the set of recorded process variables, and (ii) the set of PCs is better conditioned as redundant and insignificant information is removed. The result is a new set of input data for a modified network. The usefulness of this approach is illustrated using a recorded industrial data that relates to crack detection in an industrial melter process.

引用

页码：293 / 298

页数：6

共 50 条

[31] Principal component analysis in the environmental monitoring process
de Souza, Amaury
da Silva Santos, Debora Aparecida
[J]. NATIVA, 2018, 6 (06): : 639 - 647
[32] Randomized Kernel Principal Component Analysis for Modeling and Monitoring of Nonlinear Industrial Processes with Massive Data
Zhou, Zhe
Du, Ni
Xu, Jingyun
Li, Zuxin
Wang, Peiliang
Zhang, Jie
[J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2019, 58 (24) : 10410 - 10417
[33] Multiscale nonlinear principal component analysis (NLPCA) and its application for chemical process monitoring
Geng, ZQ
Zhu, QX
[J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2005, 44 (10) : 3585 - 3593
[34] On-line nonlinear process monitoring based on sparse kernel principal component analysis
Zhao, Zhonggai
Liu, Fei
[J]. Huagong Xuebao/Journal of Chemical Industry and Engineering (China), 2008, 59 (07): : 1773 - 1777
[35] Research on nonlinear process monitoring and fault diagnosis based on kernel principal component analysis
He, Fei
Li, Min
Yang, Jianhong
Xu, Jinwu
[J]. DAMAGE ASSESSMENT OF STRUCTURES VIII, 2009, 413-414 : 583 - 590
[36] Sparse Kernel Principal Component Analysis via Sequential Approach for Nonlinear Process Monitoring
Guo, Lingling
Wu, Ping
Gao, Jinfeng
Lou, Siwei
[J]. IEEE ACCESS, 2019, 7 : 47550 - 47563
[37] Variable window adaptive Kernel Principal Component Analysis for nonlinear nonstationary process monitoring
Ben Khediri, Issam
Limam, Mohamed
Weihs, Claus
[J]. COMPUTERS & INDUSTRIAL ENGINEERING, 2011, 61 (03) : 437 - 446
[38] A new method for process monitoring based on mixture probabilistic principal component analysis models
Zhao, Zhong-Gai
Liu, Fei
[J]. ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 3, PROCEEDINGS, 2006, 3973 : 939 - 944
[39] An Improved Principal Component Regression for Quality-Related Process Monitoring of Industrial Control Systems
Sun, Chengyuan
Hou, Jian
[J]. IEEE ACCESS, 2017, 5 : 21723 - 21730
[40] Sparse modeling and monitoring for industrial processes using sparse, distributed principal component analysis
Huang, Jian
Yang, Xu
Shardt, Yuri A. W.
Yan, Xuefeng
[J]. JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS, 2021, 122 : 14 - 22

← 1 2 3 4 5 →