Real-time prediction of cure cycle performance in polymer composite processing using Neural Networks

Pantelelis, NG; Karamitsos, A

dc.contributor.author	Pantelelis, NG	en
dc.contributor.author	Karamitsos, A	en
dc.date.accessioned	2014-03-01T02:49:34Z
dc.date.available	2014-03-01T02:49:34Z
dc.date.issued	2003	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34617
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0141729289&partnerID=40&md5=c0884652b463641aff5602c40cd85385	en
dc.subject	Cure	en
dc.subject	Neural Networks	en
dc.subject	Real time	en
dc.subject	Simulation	en
dc.subject.other	Computer simulation	en
dc.subject.other	Curing	en
dc.subject.other	Finite element method	en
dc.subject.other	Neural networks	en
dc.subject.other	Thermosets	en
dc.subject.other	Polymer composites	en
dc.subject.other	Nonmetallic matrix composites	en
dc.title	Real-time prediction of cure cycle performance in polymer composite processing using Neural Networks	en
heal.type	conferenceItem	en
heal.publicationDate	2003	en
heal.abstract	In this paper the use of Neural Networks for the on-line prediction of cure cycle performance is presented. The need of an on-line fast tool for the prediction of the cure cycle characteristics according to real time measurements of the cure process is apparent for the whole polymer composite industry. Various Neural Network architectures and set-ups are presented, discussed and tested to provide the fastest and more reliable solution. The training of the Neural Networks is performed using a 1-D simulation tool. Finally, some ideas about the implementation of this tool in the on-line control of the cure process are presented.	en
heal.journalName	Annual Technical Conference - ANTEC, Conference Proceedings	en
dc.identifier.volume	3	en
dc.identifier.spage	3280	en
dc.identifier.epage	3284	en