Open AccessSlope reliability analysis based on PSO-RBF neural network
Author(s) -
Yunlong He,
Qing Li,
Ning Zhang,
Chuangjiang Li
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1325/1/012074
Subject(s) - particle swarm optimization , reliability (semiconductor) , artificial neural network , safety factor , radial basis function , monte carlo method , random variable , function (biology) , computer science , basis (linear algebra) , algorithm , mathematics , mathematical optimization , statistics , engineering , artificial intelligence , structural engineering , physics , power (physics) , geometry , quantum mechanics , evolutionary biology , biology
In this paper, a reliability analysis method based on ABAQUS and particle swarm optimization radial basis function neural network is proposed. The strength reduction method based on ABAQUS is used to calculate the safety factor corresponding to the selected random variable. The data fitting function of the radial basis function neural network is used to establish the model and map the relationship between the safety factor and the random variable to construct the response surface function. A large number of random samples generated by Monte Carlo are substituted into the function to obtain the corresponding safety coefficient,in order to calculate the instability probability and reliability index of the slope.