基于支持向量机的隧道变形预测模型研究  

Research on tunnel displacement forecast model based on support vector machines

作　　者：刘宇[1] 

机构地区：[1]吉林铁道职业技术学院铁道工程系,吉林吉林132001

出　　处：《内蒙古科技大学学报》2015年第4期370-373,共4页Journal of Inner Mongolia University of Science and Technology

摘　　要：采用遗传算法(Genetic Algorithm,GA)对支持向量机(Support Vector Machines,SVM)的核函数参数g和惩罚因子c进行优化,建立基于参数寻优支持向量机的蠕动型滑坡隧道变形位移预测模型,以与蠕动型滑坡隧道变形密切相关的10个影响因子作为模型输入向量,隧道变形实测数据值作为模型的目标输出.以吉林省蛟河市长珲高速老爷岭隧道实地监测数据为样本对模型进行训练与预测分析,仿真结果表明:本文方法训练速度快且预测值与真实值平均相对误差小于2%,具有很强的工程应用价值.Genetic algorithm was used to optimize the penalty factor parameters c and g of support vector machines. The tunnel displacement forecast model was established based on the optimized parameters of support vector machines. The model inputs were 10 impact factors closely related to creep landslide deformation of tunnel,and the value of the measured data of the tunnel deformation were used as the target output of the model. Actual data of Laoyeling tunnel in Changchun to Hunchun highway of Jilin province were adopted as a sample to train the model and predict tunnel deformation displacement. The simulation results show that this method has a fast training speed,and the average relative error between testing value and true value is less than 2%. The method has a strong value for engineering application.

关 键 词：隧道 变形预测 支持向量机 遗传算法 

分 类 号：TU454[建筑科学—岩土工程]