基于PSO-SVM的岩石边坡稳定性预测  

Prediction of Rock Slope Stability Based on Support Vector Machine Optimized by Particle Swarm Optimization

作　　者：徐飞[1] 刘造保[2] 

机构地区：[1]海南省公路勘察设计院,海口570206 [2]河海大学岩土工程科学研究所,南京210098

出　　处：《三峡大学学报（自然科学版）》2010年第6期61-65,共5页Journal of China Three Gorges University：Natural Sciences

基　　金：国家自然科学基金(50539110);国家科技支撑计划(2008BAB29801);江苏省普通高校研究生科研创新计划(CX09B-158Z)

摘　　要：边坡稳定性与其影响因素之间存在着复杂的非线性关系.结合粒子群优化算法和支持向量机,提出了边坡稳定评价的粒子群优化支持向量机模型.模型采用支持向量机建立边坡稳定性和影响因素之间的非线性关系;同时,利用粒子群算法对支持向量机参数进行全局寻优,从而确保了模型参数的准确性.模型的测试结果显示了良好的精度.将该模型应用到某岩石高边坡中,预测结果与实际情况符合较好,表明该模型在岩石边坡稳定性预测中的可行性和有效性.The relationship between slope stability and influencing factors is complex and nonlinear.Based on the particle swarm optimization（PSO） and the support vector machine（SVM）,a new model for slope stability prediction is developed.On the one hand,the nonlinear relationship between slope stability and influencing factors is established by SVM;On the other hand,the parameters of SVM are optimized by PSO;that would ensure the accuracy of the parameters used in the model.The test results of the model show a very good precision.In this study,the prediction results obtained by applying the model developed here to a high rock slope,are well consistent with the actual situation.It is shown that the model developed is feasible and effective for slope stability prediction.

关 键 词：岩石边坡 稳定性 预测 粒子群优化 支持向量机 

分 类 号：TU443[建筑科学—岩土工程]