Reliable modelling and optimisation control of reactive polymer composite moulding processes using bootstrap aggregated neural network models

Zhang, J; Pantelelis, NG

dc.contributor.author	Zhang, J	en
dc.contributor.author	Pantelelis, NG	en
dc.date.accessioned	2014-03-01T02:53:27Z
dc.date.available	2014-03-01T02:53:27Z
dc.date.issued	2011	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/36325
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-84862211644&partnerID=40&md5=c8767588241fe24416e2de77698dce23	en
dc.subject	Bootstrap re-sampling	en
dc.subject	Modelling	en
dc.subject	Neural networks	en
dc.subject	Optimisation	en
dc.subject	Polymer composite moulding	en
dc.subject.other	Bootstrap resampling	en
dc.subject.other	Control strategies	en
dc.subject.other	Degree of cure	en
dc.subject.other	Dynamic neural networks	en
dc.subject.other	Generalisation	en
dc.subject.other	Industrial processs	en
dc.subject.other	Model prediction	en
dc.subject.other	Modelling	en
dc.subject.other	Modelling and optimisation	en
dc.subject.other	Moulding process	en
dc.subject.other	Multiple neural networks	en
dc.subject.other	Neural network model	en
dc.subject.other	Objective functions	en
dc.subject.other	Operational data	en
dc.subject.other	Optimal controls	en
dc.subject.other	Optimal heating	en
dc.subject.other	Optimisations	en
dc.subject.other	Polymer composite	en
dc.subject.other	Process operation	en
dc.subject.other	Static and dynamic	en
dc.subject.other	Training data	en
dc.subject.other	Composite materials	en
dc.subject.other	Curing	en
dc.subject.other	Forecasting	en
dc.subject.other	Molding	en
dc.subject.other	Neural networks	en
dc.subject.other	Optimization	en
dc.subject.other	Polymers	en
dc.subject.other	Aggregates	en
dc.title	Reliable modelling and optimisation control of reactive polymer composite moulding processes using bootstrap aggregated neural network models	en
heal.type	conferenceItem	en
heal.publicationDate	2011	en
heal.abstract	This paper presents using bootstrap aggregated neural networks for the modelling and optimisation control of reactive polymer composite moulding processes. Bootstrap aggregated neural networks combine multiple neural networks developed from bootstrap re-sampling replications of the original training data in order to enhance model prediction and generalisation capability. Neural network models for modelling the degree of cure (through modelling the measured resistance) are developed from real industrial process operational data. Both static and dynamic models are developed and the developed neural network models are validated on unseen process operation data. The bootstrap aggregated neural network models give accurate and reliable predictions than single neural networks. Optimal heating profile is obtained by solving an optimisation problem using the dynamic neural network model. The model prediction confidence bound is incorporated in the optimisation objective function in order to enhance the reliability of the calculated optimal control profile. In addition to maximise the final degree of cure, model prediction confidence bound is minimised. Application results on a simulated polymer composite moulding process demonstrate that the proposed reliable optimisation control strategy is effective.	en
heal.journalName	NCTA 2011 - Proceedings of the International Conference on Neural Computation Theory and Applications	en
dc.identifier.spage	236	en
dc.identifier.epage	241	en