Bidirectional Dynamic Latent Variable Analysis for Closed-Loop Process Monitoring

Xu CHEN; Xiao HE; Joe S. QIN

doi:10.1109/TIE.2023.3319731

Bidirectional Dynamic Latent Variable Analysis for Closed-Loop Process Monitoring

Xu CHEN, Xiao HE, Joe S. QIN

Research output: Journal Publications › Journal Article (refereed) › peer-review

3 Citations (Scopus)

Abstract

Closed-loop data are widely encountered in modern industrial systems, which require special data analytics to gain insight for system monitoring. A closed-loop dynamic latent analysis scheme named closed-loop DiCCA (CL-DiCCA) is proposed in this article. Bidirectional dynamic latent variable relationships are proposed with a new objective to extract the closed-loop dynamic latent structure. An iterative algorithm is proposed to solve the constructed optimization problem for closed-loop processes. Four statistically independent residuals are generated, which monitor the dynamic and static variations of the process data. A process monitoring logic with the CL-DiCCA model is established, which offers further separation of faults into output-relevant and output-irrelevant ones. A numerical simulation and a case study on the thruster system of the Jiaolong deep-sea submersible are provided to illustrate the effectiveness of the proposed method.

Original language	English
Pages (from-to)	9823-9833
Number of pages	11
Journal	IEEE Transactions on Industrial Electronics
Volume	71
Issue number	8
Early online date	23 Oct 2023
DOIs	https://doi.org/10.1109/TIE.2023.3319731
Publication status	Published - Aug 2024

Bibliographical note

Publisher Copyright:
© 1982-2012 IEEE.

Funding

This work was supported in part by the Natural Science Foundation of China under Grant 61733009 and Grant U20A20189, in part by the National Key Research and Development Program of China under Grant 2022YFB25031103, in part by Huaneng Group Science and Technology Research Project under Grant HNKJ22-H105, in part by the Natural Science Foundation of China under Grant U20A20189, in part by the Math and Application Project under Grant 2021YFA1003504, in part by the National Key R&D Program, and in part by the General Research Fund through RGC of Hong Kong under Grant 11303421.

Keywords

Bidirectional latent dynamic models
closed-loop process monitoring
Correlation
Data models
dynamic latent variable (DLV) analysis
Heuristic algorithms
Loading
Predictive models
Principal component analysis
Process monitoring

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TIE.2023.3319731

https://ieeexplore.ieee.org/document/10292504/

Cite this

@article{97a02e5443cc4dff80434cc97f7b27fb,

title = "Bidirectional Dynamic Latent Variable Analysis for Closed-Loop Process Monitoring",

abstract = "Closed-loop data are widely encountered in modern industrial systems, which require special data analytics to gain insight for system monitoring. A closed-loop dynamic latent analysis scheme named closed-loop DiCCA (CL-DiCCA) is proposed in this article. Bidirectional dynamic latent variable relationships are proposed with a new objective to extract the closed-loop dynamic latent structure. An iterative algorithm is proposed to solve the constructed optimization problem for closed-loop processes. Four statistically independent residuals are generated, which monitor the dynamic and static variations of the process data. A process monitoring logic with the CL-DiCCA model is established, which offers further separation of faults into output-relevant and output-irrelevant ones. A numerical simulation and a case study on the thruster system of the Jiaolong deep-sea submersible are provided to illustrate the effectiveness of the proposed method.",

keywords = "Bidirectional latent dynamic models, closed-loop process monitoring, Correlation, Data models, dynamic latent variable (DLV) analysis, Heuristic algorithms, Loading, Predictive models, Principal component analysis, Process monitoring",

author = "Xu CHEN and Xiao HE and QIN, {Joe S.}",

note = "Publisher Copyright: {\textcopyright} 1982-2012 IEEE.",

year = "2024",

month = aug,

doi = "10.1109/TIE.2023.3319731",

language = "English",

volume = "71",

pages = "9823--9833",

journal = "IEEE Transactions on Industrial Electronics",

issn = "0278-0046",

publisher = "IEEE Industrial Electronics Society",

number = "8",

}

TY - JOUR

T1 - Bidirectional Dynamic Latent Variable Analysis for Closed-Loop Process Monitoring

AU - CHEN, Xu

AU - HE, Xiao

AU - QIN, Joe S.

PY - 2024/8

Y1 - 2024/8

N2 - Closed-loop data are widely encountered in modern industrial systems, which require special data analytics to gain insight for system monitoring. A closed-loop dynamic latent analysis scheme named closed-loop DiCCA (CL-DiCCA) is proposed in this article. Bidirectional dynamic latent variable relationships are proposed with a new objective to extract the closed-loop dynamic latent structure. An iterative algorithm is proposed to solve the constructed optimization problem for closed-loop processes. Four statistically independent residuals are generated, which monitor the dynamic and static variations of the process data. A process monitoring logic with the CL-DiCCA model is established, which offers further separation of faults into output-relevant and output-irrelevant ones. A numerical simulation and a case study on the thruster system of the Jiaolong deep-sea submersible are provided to illustrate the effectiveness of the proposed method.

AB - Closed-loop data are widely encountered in modern industrial systems, which require special data analytics to gain insight for system monitoring. A closed-loop dynamic latent analysis scheme named closed-loop DiCCA (CL-DiCCA) is proposed in this article. Bidirectional dynamic latent variable relationships are proposed with a new objective to extract the closed-loop dynamic latent structure. An iterative algorithm is proposed to solve the constructed optimization problem for closed-loop processes. Four statistically independent residuals are generated, which monitor the dynamic and static variations of the process data. A process monitoring logic with the CL-DiCCA model is established, which offers further separation of faults into output-relevant and output-irrelevant ones. A numerical simulation and a case study on the thruster system of the Jiaolong deep-sea submersible are provided to illustrate the effectiveness of the proposed method.

KW - Bidirectional latent dynamic models

KW - closed-loop process monitoring

KW - Correlation

KW - Data models

KW - dynamic latent variable (DLV) analysis

KW - Heuristic algorithms

KW - Loading

KW - Predictive models

KW - Principal component analysis

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=85176309760&partnerID=8YFLogxK

U2 - 10.1109/TIE.2023.3319731

DO - 10.1109/TIE.2023.3319731

M3 - Journal Article (refereed)

SN - 0278-0046

VL - 71

SP - 9823

EP - 9833

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

IS - 8

ER -

Bidirectional Dynamic Latent Variable Analysis for Closed-Loop Process Monitoring

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this