摘要
为分析深基坑在开挖过程中的变形规律,为安全生产提供有效信息,采用最小二乘支持向量机理论,利用粒子群算法对支持向量机的核参数进行优化,建立深基坑水平位移预测模型,并将预测结果与实际监测结果进行对比.研究结果表明:优化后的最小二乘支持向量机模型收敛速度快,泛化能力强,预测结果与实际监测数据有很好的一致性,精度高于传统的预测模型,对深基坑安全监控有一定的实用价值.
In order to analyze the deformation regularity during the process of deformation monitoring and provide effective information for safety, Least Square Support Vector Machine was used to build the prediction model of deep foundation pit horizontal displacement. PSO algorithm was introduced to optimize the parameters of support vector machine.Compared with predicted results and actual monitoring results, it draws the conclusion that the optimized SVM model is more effective and accurate. Prediction results are very consistent with the actual monitoring results, and it has certain practical value in deep foundation pit safety monitoring.
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2014年第11期1471-1474,共4页
Journal of Liaoning Technical University (Natural Science)
基金
吉林省科技发展计划基金资助项目(20120437)
国家自然科学基金资助项目(41072196)
关键词
深基坑
水平位移
最小二乘支持向量机
粒子群算法
变形监测
deep foundation pit
horizontal displacement
least square support vector machine
PSO algorithm
deformation monitoring
