摘要
提出了一种基于主成分分析(PCA)和支持向量机(SVM)的边坡稳定性预测模型。首先分析了影响边坡稳定性的因素,采用主成分分析方法求取主成分;再将主成分作为输入对支持向量机进行训练,并利用遗传算法优化支持向量机参数;最后通过实例与常用寻参方法所得结果进行比较。结果表明,该法能减少输入变量维数,提高了边坡工程稳定性的预测精度。
A prediction model of slope stability based on principal component analysis（PCA） and support vector machine（SVM） is put forward.First,the influencing factors of slope stability are analyzed and the principal component is searched through principal component analysis.Then support vector machine is trained with principal component as the input and the parameters of support vector machine are optimized using genetic algorithm.Finally the result from the common search method is compared with engineering example.It is indicated that this method can reduce input variable dimension to improve the precision of prediction of slope stability.
出处
《路基工程》
2011年第2期5-7,共3页
Subgrade Engineering
基金
国家自然科学基金(60875034)
关键词
主成分分析
支持向量机
遗传算法
边坡稳定性
principal component analysis
support vector machine
genetic algorithm
slope stability
