Premium
Artificial intelligence techniques in simulation of viscoplasticity of polymeric composites
Author(s) -
AlHaik M.S.,
Hussaini M.Y.,
Rogan C.S.
Publication year - 2009
Publication title -
polymer composites
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.577
H-Index - 82
eISSN - 1548-0569
pISSN - 0272-8397
DOI - 10.1002/pc.20745
Subject(s) - viscoplasticity , materials science , composite number , artificial neural network , phenomenological model , composite material , matrix (chemical analysis) , computer science , artificial intelligence , finite element method , constitutive equation , structural engineering , mathematics , engineering , statistics
The viscoplastic behavior of a carbon fiber/polymer matrix composite is investigated via different modeling schemes. The first model is phenomenological in nature based on the overstress‐viscoplasticity. The second model utilizes neural networks paradigms. Genetic algorithm‐based strategies are used to prune the proposed neural network. Several optimization algorithms are implemented for training the network. In comparison, the neurocomputational model is found to outperform the phenomenological model. POLYM. COMPOS., 2009. © 2008 Society of Plastics Engineers