Proposal of an optimum cure cycle for filament winding process using a hybrid neural network ‐ first principles model
Source abstract
Abstract
The adopted cure cycle in the filament winding process must lead to a completely cured composite. However, a restriction on the temperature should be observed to avoid the resin degradation. Here, an optimum cure cycle was determined using a hybrid neural network—first principles model (HNM) of the filament winding process and the particle swarm optimization method to find the minimum of an economic objective function. HNM was based on energy and mass balances, being the cure kinetics described by a neural network model. The results showed a high degree of cure and a shorter processing time with a lesser energy demand. POLYM. COMPOS., 35:1377–1387, 2014. © 2013 Society of Plastics Engineers
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Epoxy Resin Curing Processes · Injection Molding Process and Properties · Mechanical Behavior of Composites
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Departamento de Engenharia Química Universidade Federal de Sergipe Centro de Ciências Exatas, Sala 10, Cidade Universitária CEP 49100‐000 São Cristóvão SE Brazil
Escola de Química Universidade Federal do Rio de Janeiro Centro de Tecnologia, Bloco E, Sala E‐207, Ilha do Fundão CEP 21941‐909 Rio de Janeiro RJ Brazil
Programa de Engenharia Química/COPPE Universidade Federal do Rio de Janeiro CT, Sala G‐130, Ilha do Fundão CEP 21941‐914 Rio de Janeiro RJ Brazil
References (21)
Show source-provided references
1. 10.1016/j.jmatprotec.2006.11.14610.1016/j.jmatprotec.2006.11.146 ↗
2. 10.1016/0254-0584(95)01554-X10.1016/0254-0584(95)01554-X ↗
3. 10.1177/00219983900240120210.1177/002199839002401202 ↗
4. 10.1177/00219983900240120310.1177/002199839002401203 ↗
5. 10.1177/00219983900240120410.1177/002199839002401204 ↗
6. 10.1016/S1359-835X(97)00091-210.1016/S1359-835X(97)00091-2 ↗
7. 10.1016/S0263-8223(01)00039-310.1016/S0263-8223(01)00039-3 ↗
8. 10.1002/er.88210.1002/er.882 ↗
9. 10.1016/j.ijheatmasstransfer.2004.05.01010.1016/j.ijheatmasstransfer.2004.05.010 ↗
10. 10.1002/jctb.167810.1002/jctb.1678 ↗
11. 10.1016/0893-6080(89)90003-810.1016/0893-6080(89)90003-8 ↗
12. Constant S. · Polímeros Ciência e Tecnol. · 2004 · 14 · 29510.1590/S0104-14282004000500004 ↗
13. 10.1002/aic.69038100310.1002/aic.690381003 ↗
14. 10.1002/pen.76013011010.1002/pen.760130110 ↗
15. Haykin S. · 1999
16. 10.7551/mitpress/5236.001.000110.7551/mitpress/5236.001.0001 ↗
17. 10.1016/0098-1354(90)87070-610.1016/0098-1354(90)87070-6 ↗
18. J.KennedyandR.C.Eberhart Proceedings of the IEEE International Conference on Neural Networks Vol. 4 Piscataway New Jersey 1942 (1995).10.1109/ICNN.1995.488968 ↗
19. 10.1590/S1516-1439200300040002710.1590/S1516-14392003000400027 ↗
20. 10.1002/pc.1043510.1002/pc.10435 ↗
21. R.L.Pagano V.M.A.Calado andE.C.Biscaia Proceedings of the 17th European Symposium of Computer Aided Process Engineering Vol. 1 Bucharest 1 (2007).