Applications of object-oriented Bayesian networks for causal analysis of process disturbances
- We discuss a hybrid approach for causal analysis of disturbances in industrial process operation. It represents a combination of OOBN with first level diagnostic packages and physical models serving as agents in the system design and providing evidence for automated reasoning on abnormality in process operation. The aim is causal analysis of non-measurable disturbances as a decision advice complement to the distributed control system (DCS). The approach includes prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand. The methodology has been applied on a screening process with a pressure-flow network in a Pulp Mil.
Author: | Galia WeidlORCiD, Anders L. Madsen, Erik Dahlquist |
---|---|
URL: | https://www.researchgate.net/publication/228679172_Applications_of_object-oriented_Bayesian_networks_for_causal_analysis_of_process_disturbances#fullTextFileContent |
Parent Title (English): | SIMS'2003 (44th International Conference of the Scandinavian Simulation Society) |
Document Type: | Conference Proceeding |
Language: | English |
Year of Completion: | 2003 |
Release Date: | 2023/12/07 |
Tag: | Bayesian Networks; DCS; OOBN |
GND Keyword: | Prozessmodell; Prozesssteuerung |
Urheberrecht: | 1 |
Institutes: | Einrichtungen / Kompetenzzentrum Künstliche Intelligenz |
research focus : | Intelligent Systems / Artifical Intelligence and Data Science |
Licence (German): | Creative Commons - CC BY - Namensnennung 4.0 International |