基于PSO-SVR的岩质边坡稳定性评价模型  

Stability evaluation model of rock mass slope based on PSO-SVR

作　　者：颜七笙[1,2] 王士同[1] 

机构地区：[1]江南大学信息工程学院,江苏无锡214122 [2]东华理工大学数学与信息科学学院,江西抚州344000

出　　处：《计算机工程与应用》2011年第16期235-238,共4页Computer Engineering and Applications

基　　金：江西省教育厅科技项目(No.GJJ10500)

摘　　要：针对边坡稳定性影响因素的复杂性,提出了基于粒子群算法(PSO)和支持向量回归(SVR)的边坡稳定性评价模型。该模型利用粒子群算法快速全局优化的特点和支持向量回归机对小样本数据的良好学习能力,建立了岩质边坡稳定性与其影响因素之间的非线性关系。仿真实验表明,该方法具有比BP神经网络和自适应模糊推理系统(ANFIS)方法更好的预测精度。For the complex relationships among influencing factors in slope stability,a slope stability evaluation model based on Particle Swarm Optimization（PSO） and Support Vector Regression（SVR） is proposed.The nonlinear relation between slope stability and influencing factors is obtained from the finite empirical data by SVR model, and PSO is used to search the optimum parameters of SVR.A simulation example is taken to demonstrate correctness and effectiveness of the proposed approach.The result shows that the model and algorithm proposed possess convenience,objectivity and can get higher prediction precision than BP neural network prediction and ANFIS method.

关 键 词：岩质边坡 稳定性评价 支持向量回归 粒子群算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]