Neural network calibration of moderator temperature coefficient measurements in pressurized water nuclear reactors

Simple item page
dc.contributor.authorAdams, Joseph T.en
dc.contributor.committeechairThomas, James R. Jr.en
dc.contributor.committeememberWicks, Alfred L.en
dc.contributor.committeememberPierce, Felix J.en
dc.contributor.departmentMechanical Engineeringen
dc.date.accessioned2014-03-14T21:50:54Zen
dc.date.adate2009-12-04en
dc.date.available2014-03-14T21:50:54Zen
dc.date.issued1993-05-06en
dc.date.rdate2009-12-04en
dc.date.sdate2009-12-04en
dc.description.abstractNeural networks have been shown to be capable of predicting the moderator temperature coefficient in a nuc1ear reactor by using the frequency response functions between the in-core neutron flux signal and the ex-core thermocouple signal as inputs. In this work, actual data from a nuc1ear reactor is used by neural networks to estimate the moderator temperature coefficient at different times during a fuel cycle. Along with the conventional method of training neural networks, a new method of training that better models the use of neural networks in predicting the moderator temperature coefficient is also successfully demonstrated. The results show that neural networks are effective at estimating the moderator temperature coefficient if the domain of prediction is within the training domain of the network. The advantage of using the autoregression method to create the frequency response patterns used as inputs to the neural network as opposed to frequency response functions calculated by the Fourier transform method is also shown.en
dc.description.degreeMaster of Scienceen
dc.format.extentix, 81 leavesen
dc.format.mediumBTDen
dc.format.mimetypeapplication/pdfen
dc.identifier.otheretd-12042009-020108en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-12042009-020108/en
dc.identifier.urihttp://hdl.handle.net/10919/46087en
dc.language.isoenen
dc.publisherVirginia Techen
dc.relation.haspartLD5655.V855_1993.A336.pdfen
dc.relation.isformatofOCLC# 30114375en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.lccLD5655.V855 1993.A336en
dc.subject.lcshNeural networks (Computer science)en
dc.subject.lcshNuclear reactorsen
dc.subject.lcshReactor moderatorsen
dc.titleNeural network calibration of moderator temperature coefficient measurements in pressurized water nuclear reactorsen
dc.typeThesisen
dc.type.dcmitypeTexten
thesis.degree.disciplineMechanical Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LD5655.V855_1993.A336.pdf
Size:
2.38 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses