Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis
In order to guarantee and improve the product quality, the data-driven fault detection technique has been widely used in industry. For three-way datasets of batch process in industry process (i.e., batch × variable × time), a novel method named functional local kernel principal...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9123888/ |
id |
doaj-067004fb6c4c47ec986589b656a5679e |
---|---|
record_format |
Article |
spelling |
doaj-067004fb6c4c47ec986589b656a5679e2021-03-30T02:29:54ZengIEEEIEEE Access2169-35362020-01-01811751311752710.1109/ACCESS.2020.30045649123888Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component AnalysisFei He0https://orcid.org/0000-0002-1739-5649Zhiyan Zhang1Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing, ChinaCollaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing, ChinaIn order to guarantee and improve the product quality, the data-driven fault detection technique has been widely used in industry. For three-way datasets of batch process in industry process (i.e., batch × variable × time), a novel method named functional local kernel principal component analysis (FLKPCA) is proposed. Since the variables' trajectories often show functional nature and can be considered as smooth functions rather than just vectors. Firstly, the variables' trajectory is expressed as the combination of smooth basis functions using functional data analysis (FDA), which means that the datasets of batches process would be transformed from the three-ways array into two-ways function matrix. Then, kernel locality preserving projections (LKPCA) is used to perform dimensionality reduction on two-way function matrix directly. Different from kernel principal component analysis (KPCA). LKPCA aims at preserving the both local and global structure of the data in a new optimization objective. Consequently, FLKPCA could more effectively seek the potential information that hidden in the three-ways datasets. Lastly, the effectiveness of the proposed approach is illustrated by the benchmark of fed-batch penicillin fermentation process and the hot strip rolling process.https://ieeexplore.ieee.org/document/9123888/Kernel functional local principal component analysisprocess monitoringfault detectionfunction data analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fei He Zhiyan Zhang |
spellingShingle |
Fei He Zhiyan Zhang Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis IEEE Access Kernel functional local principal component analysis process monitoring fault detection function data analysis |
author_facet |
Fei He Zhiyan Zhang |
author_sort |
Fei He |
title |
Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis |
title_short |
Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis |
title_full |
Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis |
title_fullStr |
Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis |
title_full_unstemmed |
Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis |
title_sort |
nonlinear fault detection of batch processes using functional local kernel principal component analysis |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
In order to guarantee and improve the product quality, the data-driven fault detection technique has been widely used in industry. For three-way datasets of batch process in industry process (i.e., batch × variable × time), a novel method named functional local kernel principal component analysis (FLKPCA) is proposed. Since the variables' trajectories often show functional nature and can be considered as smooth functions rather than just vectors. Firstly, the variables' trajectory is expressed as the combination of smooth basis functions using functional data analysis (FDA), which means that the datasets of batches process would be transformed from the three-ways array into two-ways function matrix. Then, kernel locality preserving projections (LKPCA) is used to perform dimensionality reduction on two-way function matrix directly. Different from kernel principal component analysis (KPCA). LKPCA aims at preserving the both local and global structure of the data in a new optimization objective. Consequently, FLKPCA could more effectively seek the potential information that hidden in the three-ways datasets. Lastly, the effectiveness of the proposed approach is illustrated by the benchmark of fed-batch penicillin fermentation process and the hot strip rolling process. |
topic |
Kernel functional local principal component analysis process monitoring fault detection function data analysis |
url |
https://ieeexplore.ieee.org/document/9123888/ |
work_keys_str_mv |
AT feihe nonlinearfaultdetectionofbatchprocessesusingfunctionallocalkernelprincipalcomponentanalysis AT zhiyanzhang nonlinearfaultdetectionofbatchprocessesusingfunctionallocalkernelprincipalcomponentanalysis |
_version_ |
1724185033031286784 |