Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICNSC.2010.5461510
Title: Decision fusion in distributed multi agent process supervisory system
Authors: Ghosh, K.
Natarajan, S. 
Srinivasan, R. 
Keywords: Decision fusion
Distributed system
Fault detection and identification
Multi agent systems
Ontology
Issue Date: 2010
Source: Ghosh, K.,Natarajan, S.,Srinivasan, R. (2010). Decision fusion in distributed multi agent process supervisory system. 2010 International Conference on Networking, Sensing and Control, ICNSC 2010 : 183-188. ScholarBank@NUS Repository. https://doi.org/10.1109/ICNSC.2010.5461510
Abstract: Process supervisory systems in large scale chemical plants have traditionally relied on single monolithic methods. However, most faults occur at an equipment level which if allowed to propagate results in leaks, fires, explosions causing loss of life, capital invested and production downtime. Monitoring the overall process for detection of such equipment failures may be futile as deviations in the process are often lagging indicators by which time plant safety may be compromised. Moreover, modern sensors and equipments have their own smart diagnostic capability which a process monitoring system should make use of. Hence, we propose a distributed process monitoring system which uses multiple FDI methods/agents capable of monitoring the plant at various sections and varying levels of granularity (tag level to unit level). When multiple FDI agents are used they need to effectively interact with one another. Hence, a custom ontology is developed to explicitly capture the hierarchy of the process and the nature of the faults. A key issue in monitoring any complex system using multiple independent methods in parallel is that the individual methods may not always concur. A suitable decision fusion/consolidator agent is used which performs the matching between the results from the various FDI agents by mapping their evidences to the ontology and seeking coherence among the various evidences. The proposed approach has been implemented as a multi-agent system using Java WADE distributed environment. The efficacy of this system is demonstrated on a distillation column case study. ©2010 IEEE.
Source Title: 2010 International Conference on Networking, Sensing and Control, ICNSC 2010
URI: http://scholarbank.nus.edu.sg/handle/10635/74534
ISBN: 9781424464531
DOI: 10.1109/ICNSC.2010.5461510
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

2
checked on Dec 13, 2017

Page view(s)

16
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.