Modelling of Explosive Welding Process using GMDH-type Neural Networks and Genetic Algorithms

N. Nariman-zadeh, A. Darvizeh, and G.R. Ahmad-zadeh (Iran)


GMDH, Explosive Welding, SVD, Genetic Algorithm


GMDH-type neural networks (Group Method of Data Handling) are deployed to derive polynomials for the modelling of explosive welding process of plates. In this way, Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed simultaneously for optimal design of both connectivity configuration and the values of coefficients, respectively, involved in such GMDH-type neural networks. It is also demonstrated that singular value decomposition (SVD) can be effectively used to find the vector of coefficients of a quadratic sub expression embodied in such GMDH-type networks. Such application of SVD will improve the performance of GMDH-type networks to model the very complex process of explosive welding of plates by shaped charges.

Important Links:

Go Back