Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization

A multimode process monitoring method based on multiblock projection nonnegative matrix factorization (MPNMF) is proposed for traditional process monitoring methods which often adopt global model of data and ignore local information of data. Firstly, the training data set of each mode is partitioned...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Wang, Yu-Bo Zhao, Chuang Li, Chuan-Qian Zhu, Shuai-shuai Han, Xiao-Guang Gu
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Advances in Mathematical Physics
Online Access:http://dx.doi.org/10.1155/2020/4610493
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850159235513450496
author Yan Wang
Yu-Bo Zhao
Chuang Li
Chuan-Qian Zhu
Shuai-shuai Han
Xiao-Guang Gu
author_facet Yan Wang
Yu-Bo Zhao
Chuang Li
Chuan-Qian Zhu
Shuai-shuai Han
Xiao-Guang Gu
author_sort Yan Wang
collection DOAJ
description A multimode process monitoring method based on multiblock projection nonnegative matrix factorization (MPNMF) is proposed for traditional process monitoring methods which often adopt global model of data and ignore local information of data. Firstly, the training data set of each mode is partitioned by the complete link algorithm and the multivariate data space is divided into several subblocks. Then, the projection nonnegative matrix factorization (PNMF) algorithm is used to model each subspace of each mode separately. A joint probabilistic statistic index is defined to identify the running modes of the process data. Finally, the Bayesian information criterion (BIC) is used to synthesize the statistics of each subblock and construct a new statistic for process monitoring. The proposed process monitoring method is applied to the TE process to verify its effectiveness.
format Article
id doaj-art-b0fb13dab09d4ff09cece2d55dbaf4da
institution OA Journals
issn 1687-9120
1687-9139
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Advances in Mathematical Physics
spelling doaj-art-b0fb13dab09d4ff09cece2d55dbaf4da2025-08-20T02:23:36ZengWileyAdvances in Mathematical Physics1687-91201687-91392020-01-01202010.1155/2020/46104934610493Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix FactorizationYan Wang0Yu-Bo Zhao1Chuang Li2Chuan-Qian Zhu3Shuai-shuai Han4Xiao-Guang Gu5School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaIntelligent Manufacturing Big Data Platform (Zhengzhou) R&D Center, Zhengzhou Normal University, Zhengzhou 450044, ChinaA multimode process monitoring method based on multiblock projection nonnegative matrix factorization (MPNMF) is proposed for traditional process monitoring methods which often adopt global model of data and ignore local information of data. Firstly, the training data set of each mode is partitioned by the complete link algorithm and the multivariate data space is divided into several subblocks. Then, the projection nonnegative matrix factorization (PNMF) algorithm is used to model each subspace of each mode separately. A joint probabilistic statistic index is defined to identify the running modes of the process data. Finally, the Bayesian information criterion (BIC) is used to synthesize the statistics of each subblock and construct a new statistic for process monitoring. The proposed process monitoring method is applied to the TE process to verify its effectiveness.http://dx.doi.org/10.1155/2020/4610493
spellingShingle Yan Wang
Yu-Bo Zhao
Chuang Li
Chuan-Qian Zhu
Shuai-shuai Han
Xiao-Guang Gu
Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
Advances in Mathematical Physics
title Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
title_full Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
title_fullStr Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
title_full_unstemmed Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
title_short Multimode Process Monitoring Method Based on Multiblock Projection Nonnegative Matrix Factorization
title_sort multimode process monitoring method based on multiblock projection nonnegative matrix factorization
url http://dx.doi.org/10.1155/2020/4610493
work_keys_str_mv AT yanwang multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization
AT yubozhao multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization
AT chuangli multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization
AT chuanqianzhu multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization
AT shuaishuaihan multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization
AT xiaoguanggu multimodeprocessmonitoringmethodbasedonmultiblockprojectionnonnegativematrixfactorization