Modelling the monotonic and cyclic behaviour of sands using Artificial Neural Networks

In this study artificial neural networks (ANN) are used to simulate the monotonic and cyclic behaviour of sands observed in laboratory tests on Karlsruhe sand under drained undrained conditions. A genetic algorithm (GA) is obtain an optimal framework for ANN. The results show that proposed adaptive network (GANN) can effectively triaxial saturated isotropic or anisotropic consolidation. GANN also able predict satisfactorily test with strain stress cycles. addition, distinguish between conditions by delivering a good prediction when trained combined database.