PARALLEL-PROCESSING, NEURAL NETWORKS AND GENETIC ALGORITHMS

In an earlier paper(1) some recent developments in computational techn ology to structural engineering were described. The developments inclu ded: parallel and distributed computing; neural networks; and genetic algorithms. In this paper, the authors concentrate on parallel impleme ntations of neural networks and genetic algorithms. In the final secti on of the paper the authors show how a parallel finite element analysi s may be undertaken in an efficient manner by preprocessing of the fin ite element model using a genetic algorithm utilizing a neural network predictor. This preprocessing is the partitioning of the finite eleme nt mesh into sub-domains to ensure load balancing and minimum interpro cessor communication during the parallel finite element analysis on a MIMD distributed memory computer. (C) 1998 Published by Elsevier Scien ce Limited. All rights reserved.