基于LS-SVM的基坑最大水平位移预测模型  

Maximal Horizontal Displacement Prediction Model of Foundation Pit Based on LS-SVM

作　　者：徐洪钟[1] 周元[1] 杨磊[1] 

机构地区：[1]南京工业大学交通学院,江苏南京210009

出　　处：《水电能源科学》2011年第9期123-125,共3页Water Resources and Power

基　　金：江苏省基础研究计划基金资助项目(BK2006565);国家自然科学基金资助项目(41072217)

摘　　要：基于已施工的基坑工程监测资料,提取对基坑变形影响明显的因素,以基坑变形的各影响因素作为模型输入和基坑的最大水平位移作为输出,建立了LS-SVM预测模型,利用该模型对拟开挖基坑进行了变形预测,并将预测结果与BP神经网络模型预测结果进行了比较。结果表明,该模型预测精度较高,且泛化能力强。Based on monitoring data of foundation pit,deformation influencing factors of foundation pit is extracted.And then the Least squares support vector machine（LS-SVM） prediction model of foundation pit is built by taking the deformation influencing factors as the model input and taking the maximal horizontal displacement as the model output.Finally,the deformation of new foundation pit is predicted by using LS-SVM model.At the same time,performance of LS-SVM model is compared with BP network.The results show that the proposed model has high precision and strong generalization performance.

关 键 词：最小二乘支持向量机 基坑 最大水平位移 预测 

分 类 号：TV551.4[水利工程—水利水电工程]