Reliability analysis method based on optimization neural network- uniform experimental and its application in for slope stability

According to the current engineering design standards, the single safety factor criteria for slope stability evaluation, derived from the rigid limit equilibrium method or finite element method (FEM), may not include some important information, especially for steep slopes with complex geological conditions. This paper presents a new reliability method that uses Uniform Experiment and Neural Network. Based on the design of uniform experimental, a new structural reliability calculation analysis method is presented, which is organically combined the stochastic with artificial neural network. The method adopt by the artificial neural network instead of FEM, which can greatly reduce calculation work. Firstly, according to the random variable distribution, the limited samples are extracted by uniform experimental, which can make the FEM calculation more effective based on uniform experimental. Then, the optimize artificial neural network is set up with the limited training samples based on finite element analysis result, which has a highly nonlinear mapping relationship between the efficacy and response of the structure. By making use of the merit of artificial neural network instead of the performance function. At last Slope stability analysis of the practical Slope Stability Project is used as an example, and the conclusion can be obtained that the present method is reasonable and practicable for the reliability analysis of slopes Stability with complex conditions.