Online monitoring and diagnosis of batch processes

Empirical model-based framework and a case study

Hyun Woo Cho, Kwang Jae Kim, Myong-Kee Jeong

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

An empirical model-based framework for monitoring and diagnosing batch processes is proposed. With the input of past successful and unsuccessful batches, the off-line portion of the framework constructs empirical models. Using online process data of a new batch, the online portion of the framework makes monitoring and diagnostic decisions in a real-time basis. The proposed framework consists of three phases: monitoring, diagnostic screening, and diagnosis. For monitoring and diagnosis purposes, the multiway principal-component analysis (MPCA) model and discriminant model are adopted as reference models. As an intermediate step, the diagnostic screening phase narrows down the possible cause candidates of the fault in question. By analysing the MPCA monitoring model, the diagnostic screening phase constructs a variable influence model to screen out unlikely cause candidates. The performance of the proposed framework is tested using a real dataset from a PVC batch process. It has been shown that the proposed framework produces reliable diagnosis results. Moreover, the inclusion of the diagnostic screening phase as a pre-diagnostic step has improved the diagnosis performance of the proposed framework, especially in the early time intervals.

Original languageEnglish (US)
Pages (from-to)2361-2378
Number of pages18
JournalInternational Journal of Production Research
Volume44
Issue number12
DOIs
StatePublished - Jun 15 2006
Externally publishedYes

Fingerprint

Monitoring
Screening
Principal component analysis
Empirical model
Batch
Polyvinyl chlorides
Diagnostics

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering
  • Strategy and Management
  • Management Science and Operations Research

Cite this

@article{6b687b922b154022963cb1f12eb97edc,
title = "Online monitoring and diagnosis of batch processes: Empirical model-based framework and a case study",
abstract = "An empirical model-based framework for monitoring and diagnosing batch processes is proposed. With the input of past successful and unsuccessful batches, the off-line portion of the framework constructs empirical models. Using online process data of a new batch, the online portion of the framework makes monitoring and diagnostic decisions in a real-time basis. The proposed framework consists of three phases: monitoring, diagnostic screening, and diagnosis. For monitoring and diagnosis purposes, the multiway principal-component analysis (MPCA) model and discriminant model are adopted as reference models. As an intermediate step, the diagnostic screening phase narrows down the possible cause candidates of the fault in question. By analysing the MPCA monitoring model, the diagnostic screening phase constructs a variable influence model to screen out unlikely cause candidates. The performance of the proposed framework is tested using a real dataset from a PVC batch process. It has been shown that the proposed framework produces reliable diagnosis results. Moreover, the inclusion of the diagnostic screening phase as a pre-diagnostic step has improved the diagnosis performance of the proposed framework, especially in the early time intervals.",
author = "Cho, {Hyun Woo} and Kim, {Kwang Jae} and Myong-Kee Jeong",
year = "2006",
month = "6",
day = "15",
doi = "https://doi.org/10.1080/00207540500422130",
language = "English (US)",
volume = "44",
pages = "2361--2378",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "12",

}

Online monitoring and diagnosis of batch processes : Empirical model-based framework and a case study. / Cho, Hyun Woo; Kim, Kwang Jae; Jeong, Myong-Kee.

In: International Journal of Production Research, Vol. 44, No. 12, 15.06.2006, p. 2361-2378.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online monitoring and diagnosis of batch processes

T2 - Empirical model-based framework and a case study

AU - Cho, Hyun Woo

AU - Kim, Kwang Jae

AU - Jeong, Myong-Kee

PY - 2006/6/15

Y1 - 2006/6/15

N2 - An empirical model-based framework for monitoring and diagnosing batch processes is proposed. With the input of past successful and unsuccessful batches, the off-line portion of the framework constructs empirical models. Using online process data of a new batch, the online portion of the framework makes monitoring and diagnostic decisions in a real-time basis. The proposed framework consists of three phases: monitoring, diagnostic screening, and diagnosis. For monitoring and diagnosis purposes, the multiway principal-component analysis (MPCA) model and discriminant model are adopted as reference models. As an intermediate step, the diagnostic screening phase narrows down the possible cause candidates of the fault in question. By analysing the MPCA monitoring model, the diagnostic screening phase constructs a variable influence model to screen out unlikely cause candidates. The performance of the proposed framework is tested using a real dataset from a PVC batch process. It has been shown that the proposed framework produces reliable diagnosis results. Moreover, the inclusion of the diagnostic screening phase as a pre-diagnostic step has improved the diagnosis performance of the proposed framework, especially in the early time intervals.

AB - An empirical model-based framework for monitoring and diagnosing batch processes is proposed. With the input of past successful and unsuccessful batches, the off-line portion of the framework constructs empirical models. Using online process data of a new batch, the online portion of the framework makes monitoring and diagnostic decisions in a real-time basis. The proposed framework consists of three phases: monitoring, diagnostic screening, and diagnosis. For monitoring and diagnosis purposes, the multiway principal-component analysis (MPCA) model and discriminant model are adopted as reference models. As an intermediate step, the diagnostic screening phase narrows down the possible cause candidates of the fault in question. By analysing the MPCA monitoring model, the diagnostic screening phase constructs a variable influence model to screen out unlikely cause candidates. The performance of the proposed framework is tested using a real dataset from a PVC batch process. It has been shown that the proposed framework produces reliable diagnosis results. Moreover, the inclusion of the diagnostic screening phase as a pre-diagnostic step has improved the diagnosis performance of the proposed framework, especially in the early time intervals.

UR - http://www.scopus.com/inward/record.url?scp=53849110111&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=53849110111&partnerID=8YFLogxK

U2 - https://doi.org/10.1080/00207540500422130

DO - https://doi.org/10.1080/00207540500422130

M3 - Article

VL - 44

SP - 2361

EP - 2378

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 12

ER -