Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο: https://hdl.handle.net/20.500.14279/2515
Πεδίο DCΤιμήΓλώσσα
dc.contributor.authorChristodoulou, Constantinosen
dc.contributor.authorDemosthenous, Demosen
dc.contributor.authorCleanthous, Arisen
dc.contributor.authorNeocleous, Costas-
dc.contributor.otherΝεοκλέους, Κώστας-
dc.date.accessioned2009-07-29T07:43:05Zen
dc.date.accessioned2013-05-17T05:30:03Z-
dc.date.accessioned2015-12-02T11:28:12Z-
dc.date.available2009-07-29T07:43:05Zen
dc.date.available2013-05-17T05:30:03Z-
dc.date.available2015-12-02T11:28:12Z-
dc.date.issued2007en
dc.identifier.citationproceedings of the 25th IASTED International Multi Conference on Artificial Intelligence and Applications, February 12-14, 2007, Innsbruck, Austriaen
dc.identifier.isbn9780889866264en
dc.description.abstractThe safety of gas cylinders in domestic applications is of utmost importance. A crucial stage in the appraisal of the risk for failures and possible faults is occurring during the filling process. In Cyprus, this task is currently done by specialized workers who monitor the cylinders during filling. In order to explore the possibility for an automated risk appraisal and consequent screening, a system of fault identification using vibrational time series and neural network classification has been used. Two systems have been attempted. One using a multi-slab feedforward neural structure employing backpropagation-type learning, and a Kohonen self-organizing map. The results were also compared with different simple statistical methods. The feedforward net, proved to be slightly better responding than the Kohonen map for this particular problem.en
dc.formatpdfen
dc.language.isoenen
dc.subjectFeedforward neural networksen
dc.subjectKohonen networken
dc.subjectGas cylinderen
dc.titleNeural networks for the identification of gas cylinder faultsen
dc.typeConference Papersen
dc.dept.handle123456789/54en
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.grantfulltextopen-
item.openairecristypehttp://purl.org/coar/resource_type/c_c94f-
item.cerifentitytypePublications-
item.openairetypeconferenceObject-
crisitem.author.deptDepartment of Mechanical Engineering and Materials Science and Engineering-
crisitem.author.deptDepartment of Mechanical Engineering and Materials Science and Engineering-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.orcid0000-0001-9898-261X-
crisitem.author.parentorgFaculty of Engineering and Technology-
crisitem.author.parentorgFaculty of Engineering and Technology-
Εμφανίζεται στις συλλογές:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
Αρχεία σε αυτό το τεκμήριο:
Αρχείο Περιγραφή ΜέγεθοςΜορφότυπος
neural networks.pdf658.61 kBAdobe PDFΔείτε/ Ανοίξτε
CORE Recommender
Δείξε τη σύντομη περιγραφή του τεκμηρίου

Page view(s)

444
Last Week
0
Last month
29
checked on 13 Μαρ 2025

Download(s) 50

130
checked on 13 Μαρ 2025

Google ScholarTM

Check

Altmetric


Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα