Simulation of Stress-Strain Behavior of Saturated Sand in Undrained Triaxial Tests Based on Genetic Adaptive Neural Networks
نویسنده
چکیده
This study applies artificial neural networks (ANN) to simulate the soil stress-strain relationship observed in test data from triaxial shear testing of saturated sand. A genetic algorithm is used to obtain an optimal framework for the ANN. The results show that the proposed genetic adaptive neural network (GANN) can effectively model undrained monotonic and cyclic triaxial behaviour of saturated sand under isotropic or anisotropic consolidation. Therefore, the proposed GANN soil behaviour simulation can be used as a simple, reliable and practical analysis method.
منابع مشابه
Impact of Fiber Reinforcement on Deformation Characteristics of Cemented Sand-Gravel Mixtures
This paper describes triaxial compression tests conducted to determine the effect of fiber inclusion on stiffness and deformation characteristics of sand-gravel mixtures. Tested soil was a mixture of Babolsar sand from the shores of the Caspian Sea and Karaj River gravel. Portland cement was used as the cementing agent and fibers 12mm in length and 0.023mm in diameter at 0%, 0.5% and 1.0% were ...
متن کاملAn elasto-plastic model to describe the undrained cyclic behavior of saturated sand with initial static shear
With the aim of simulating the behavior of saturated sand with initial static shear (i.e., sloped ground) undergoing undrained cyclic loading, which leads to liquefaction and large cyclic shear strain development, an elastoplastic constitutive model which can describe both monotonic and cyclic torsional shear behaviors of saturated sand under drained and/or undrained conditions is presented. It...
متن کاملStudying the effect of inherent anisotropy on undrained behavior of sand-silt mixtures
In some situations, dams need to be built on non-rock alluvial grounds such as sand and sand-silt deposits. Therefore, undrained behavior and strength of silty sands are of great importance. One of the critical factors in studying the behavior of sand-silt mixtures is inherent anisotropy, a natural soil characteristic that depends on its texture and is independent of the soil's initial stress s...
متن کاملModelling of Stress-Strain Behaviour of Clayey Soils Using Artificial Neural Network
In this research, behaviour of clayey soils under triaxial loading is studied using Neural Network. The models have been prepared to predict the stress-strain behaviour of remolded clays under undrained condition. The advantage of the model developed is that simple parameters such as physical characteristics of soils like water content, fine content, Atterberg limits and so on, are used to mode...
متن کاملModelling of Stress-Strain Behaviour of Clayey Soils Using Artificial Neural Network
In this research, behaviour of clayey soils under triaxial loading is studied using Neural Network. The models have been prepared to predict the stress-strain behaviour of remolded clays under undrained condition. The advantage of the model developed is that simple parameters such as physical characteristics of soils like water content, fine content, Atterberg limits and so on, are used to mode...
متن کامل