ABSTRACT
In this paper, the authors explain some developments they have made in the designing of more powerful neural networks for the modeling of Bouc-Wen materials with the purpose of application in the analysis of nonlinear frame structures subject to earthquakes. The authors have developed a new type of activation function based on the Prandtl- Ishlinskii operator to incorporate in the feed forward neural networks. It is shown that the neural network is capable of learning to predict the behaviour of a structure made from Bouc-Wen material with high precision and filter the noisy data too. Genetic Algorithm has been used in the training of the neural networks.
