Prediction-based diagnosis and loss prevention using qualitative multi-scale models

E. Németh, R. Lakner, K. Hangos, I. T. Cameron

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

A prototype prediction based intelligent diagnostic system that is capable of integrating qualitative and quantitative process models and operational experience in the form of HAZOP result tables is proposed in this paper. The diagnostic system utilizes Gensym's real time G2 expert system software. Its diagnostic "cause-effect" rules and possible actions (suggestions) are extracted from the results of standard HAZOP analysis. The knowledge base of the system is organized in a hierarchical way following the hierarchy levels of a multi-scale model of the process system. This supports focusing used by fault detection and loss prevention and thus decomposes the otherwise computationally hard problem. Prediction by simplified dynamic models are used to reduce ambiguity in case of multiple possible causes and/or multiple possible mitigating actions. The system is illustrated on the example of a commercial fertilizer granulator circuit using a simulation test bed.

Original languageEnglish
Pages (from-to)1916-1930
Number of pages15
JournalInformation Sciences
Volume177
Issue number8
DOIs
Publication statusPublished - Apr 15 2007

Fingerprint

Loss prevention
Multiscale Model
Granulators
Prediction
Fertilizers
Diagnostics
Fault detection
Expert systems
Dynamic models
Networks (circuits)
Real-time Systems
Fault Detection
Expert System
Knowledge Base
Testbed
Process Model
Tables
Dynamic Model
Prototype
Decompose

Keywords

  • Diagnosis
  • HAZOP analysis
  • Multi-scale modelling
  • Process systems
  • Systems engineering

ASJC Scopus subject areas

  • Statistics and Probability
  • Electrical and Electronic Engineering
  • Statistics, Probability and Uncertainty
  • Information Systems and Management
  • Information Systems
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Prediction-based diagnosis and loss prevention using qualitative multi-scale models. / Németh, E.; Lakner, R.; Hangos, K.; Cameron, I. T.

In: Information Sciences, Vol. 177, No. 8, 15.04.2007, p. 1916-1930.

Research output: Contribution to journalArticle

Németh, E. ; Lakner, R. ; Hangos, K. ; Cameron, I. T. / Prediction-based diagnosis and loss prevention using qualitative multi-scale models. In: Information Sciences. 2007 ; Vol. 177, No. 8. pp. 1916-1930.
@article{75215511a8e94aa28fcbff3a6a7ee99a,
title = "Prediction-based diagnosis and loss prevention using qualitative multi-scale models",
abstract = "A prototype prediction based intelligent diagnostic system that is capable of integrating qualitative and quantitative process models and operational experience in the form of HAZOP result tables is proposed in this paper. The diagnostic system utilizes Gensym's real time G2 expert system software. Its diagnostic {"}cause-effect{"} rules and possible actions (suggestions) are extracted from the results of standard HAZOP analysis. The knowledge base of the system is organized in a hierarchical way following the hierarchy levels of a multi-scale model of the process system. This supports focusing used by fault detection and loss prevention and thus decomposes the otherwise computationally hard problem. Prediction by simplified dynamic models are used to reduce ambiguity in case of multiple possible causes and/or multiple possible mitigating actions. The system is illustrated on the example of a commercial fertilizer granulator circuit using a simulation test bed.",
keywords = "Diagnosis, HAZOP analysis, Multi-scale modelling, Process systems, Systems engineering",
author = "E. N{\'e}meth and R. Lakner and K. Hangos and Cameron, {I. T.}",
year = "2007",
month = "4",
day = "15",
doi = "10.1016/j.ins.2006.10.009",
language = "English",
volume = "177",
pages = "1916--1930",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "8",

}

TY - JOUR

T1 - Prediction-based diagnosis and loss prevention using qualitative multi-scale models

AU - Németh, E.

AU - Lakner, R.

AU - Hangos, K.

AU - Cameron, I. T.

PY - 2007/4/15

Y1 - 2007/4/15

N2 - A prototype prediction based intelligent diagnostic system that is capable of integrating qualitative and quantitative process models and operational experience in the form of HAZOP result tables is proposed in this paper. The diagnostic system utilizes Gensym's real time G2 expert system software. Its diagnostic "cause-effect" rules and possible actions (suggestions) are extracted from the results of standard HAZOP analysis. The knowledge base of the system is organized in a hierarchical way following the hierarchy levels of a multi-scale model of the process system. This supports focusing used by fault detection and loss prevention and thus decomposes the otherwise computationally hard problem. Prediction by simplified dynamic models are used to reduce ambiguity in case of multiple possible causes and/or multiple possible mitigating actions. The system is illustrated on the example of a commercial fertilizer granulator circuit using a simulation test bed.

AB - A prototype prediction based intelligent diagnostic system that is capable of integrating qualitative and quantitative process models and operational experience in the form of HAZOP result tables is proposed in this paper. The diagnostic system utilizes Gensym's real time G2 expert system software. Its diagnostic "cause-effect" rules and possible actions (suggestions) are extracted from the results of standard HAZOP analysis. The knowledge base of the system is organized in a hierarchical way following the hierarchy levels of a multi-scale model of the process system. This supports focusing used by fault detection and loss prevention and thus decomposes the otherwise computationally hard problem. Prediction by simplified dynamic models are used to reduce ambiguity in case of multiple possible causes and/or multiple possible mitigating actions. The system is illustrated on the example of a commercial fertilizer granulator circuit using a simulation test bed.

KW - Diagnosis

KW - HAZOP analysis

KW - Multi-scale modelling

KW - Process systems

KW - Systems engineering

UR - http://www.scopus.com/inward/record.url?scp=33846649164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846649164&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2006.10.009

DO - 10.1016/j.ins.2006.10.009

M3 - Article

AN - SCOPUS:33846649164

VL - 177

SP - 1916

EP - 1930

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 8

ER -