Application of neural networks to the modelling of some constitutive laws

This study investigates the modelling of constitutive laws of materials by neural networks. Material behaviour is no longer represented mathematically but is described by neuronal modelling. The main aim is to build a neural network directly from experimental results (the learning phase). We give se veral examples of constitutive laws (Hooke, Sargin, etc.) using a backpropa gation algorithm. Then we show that abilities of adjustment, memorisation a nd anticipation of neural networks permit us to develop a method of classif ication of constitutive laws. (C) 1999 Elsevier Science Ltd. All rights res erved.