New nested adaptive neural networks (NANN) for constitutive modeling

Abstract

Abstract The concept of using neural networks in constitutive modeling has been proposed by the first author and his co-workers. In this methodology, neural networks are trained directly with the results of material tests, and the trained neural networks can be used in analysis of boundary value problems similar to any other material model. In this paper, we introduce nested adaptive neural networks, a new type of neural network developed by Ghaboussi and his co-workers, and apply this neural network in modeling of the constitutive behavior of geomaterials. Nested adaptive neural networks take advantage of the nested structure of the material test data, and reflect it in the architecture of the neural network. This new neural network is applied in modeling of the drained and undrained behavior of sand in triaxial tests.