Fault Detection and Diagnosis in a Sour Gas Absorption Column Using Neural Networks

Hdl Handle:
http://hdl.handle.net/10149/594531
Title:
Fault Detection and Diagnosis in a Sour Gas Absorption Column Using Neural Networks
Authors:
Behbahani, R. M. (Reza Mosayyebi); Jazayeri-Rad, H.; Hajimirzaee, S. (Saeed)
Affiliation:
Teesside University. Technology Futures Institute.
Citation:
Behbahani, R. M., Jazayeri-Rad, H., Hajimirzaee, S. (2009) 'Fault Detection and Diagnosis in a Sour Gas Absorption Column Using Neural Networks' Chemical Engineering & Technology; 32 (5):840-845.
Publisher:
Wiley
Journal:
Chemical Engineering & Technology
Issue Date:
May-2009 ; 25-Apr-2009
URI:
http://hdl.handle.net/10149/594531
DOI:
10.1002/ceat.200800486
Additional Links:
http://doi.wiley.com/10.1002/ceat.200800486
Abstract:
Process fault detection and diagnosis is an important problem in plant control at the supervisory level. It is the central component of abnormal event management which has attracted a lot of attention recently. In this study, the use of artificial neural networks (ANN) for fault detection is explored. An ANN can represent nonlinear and complex relations between its inputs (sensor measurements) and outputs (faults). As a test case, absorption of CO2 gas in monoethanolamine (MEA) by a pilot plant called “automatic absorption and stripping pilot plant” is studied. For detecting and diagnosis of faults, variations in feed rate, feed composition, liquid absorber rate and composition are imposed onto the plant. The faults in this process influence variables such as the composition of absorbed gas (CO2) and temperature and pressure drop of the column. The CO2 concentration in the product should not exceed a certain limit. By selecting a proper architecture for the network (5-9-10), it is possible to detect the faults accurately. The network is trained using the back propagation method. The developed fault diagnosis algorithm is tested using data that has not been seen by the network.
Type:
Article
Language:
en
Keywords:
Artificial neural network; CO2 absorption; Fault diagnosis; Packed columns
ISSN:
09307516
Sponsors:
National Iranian Gas Company

Full metadata record

DC FieldValue Language
dc.contributor.authorBehbahani, R. M. (Reza Mosayyebi)en
dc.contributor.authorJazayeri-Rad, H.en
dc.contributor.authorHajimirzaee, S. (Saeed)en
dc.date.accessioned2016-01-21T17:15:44Zen
dc.date.available2016-01-21T17:15:44Zen
dc.date.issued2009-05en
dc.date.issued2009-04-25en
dc.identifier.citationChemical Engineering & Technology; 32 (5):840-845.en
dc.identifier.issn09307516en
dc.identifier.doi10.1002/ceat.200800486en
dc.identifier.urihttp://hdl.handle.net/10149/594531en
dc.description.abstractProcess fault detection and diagnosis is an important problem in plant control at the supervisory level. It is the central component of abnormal event management which has attracted a lot of attention recently. In this study, the use of artificial neural networks (ANN) for fault detection is explored. An ANN can represent nonlinear and complex relations between its inputs (sensor measurements) and outputs (faults). As a test case, absorption of CO2 gas in monoethanolamine (MEA) by a pilot plant called “automatic absorption and stripping pilot plant” is studied. For detecting and diagnosis of faults, variations in feed rate, feed composition, liquid absorber rate and composition are imposed onto the plant. The faults in this process influence variables such as the composition of absorbed gas (CO2) and temperature and pressure drop of the column. The CO2 concentration in the product should not exceed a certain limit. By selecting a proper architecture for the network (5-9-10), it is possible to detect the faults accurately. The network is trained using the back propagation method. The developed fault diagnosis algorithm is tested using data that has not been seen by the network.en
dc.description.sponsorshipNational Iranian Gas Companyen
dc.language.isoenen
dc.publisherWileyen
dc.relation.urlhttp://doi.wiley.com/10.1002/ceat.200800486en
dc.subjectArtificial neural networken
dc.subjectCO2 absorptionen
dc.subjectFault diagnosisen
dc.subjectPacked columnsen
dc.titleFault Detection and Diagnosis in a Sour Gas Absorption Column Using Neural Networksen
dc.typeArticleen
dc.contributor.departmentTeesside University. Technology Futures Institute.en
dc.identifier.journalChemical Engineering & Technologyen
or.citation.harvardBehbahani, R. M., Jazayeri-Rad, H., Hajimirzaee, S. (2009) 'Fault Detection and Diagnosis in a Sour Gas Absorption Column Using Neural Networks' Chemical Engineering & Technology; 32 (5):840-845.en
dc.date.accepted2008-12-17en
All Items in TeesRep are protected by copyright, with all rights reserved, unless otherwise indicated.