摘要
基坑工程可靠度传统分析方法误差和计算量较大。为了解决上述问题,本文引入支持向量机算法,并与均匀试验相结合,建立了基于支持向量机响应面的地铁基坑风险分析方法。利用均匀试验构造学习样本,并且支持向量机学习样本,从而建立了样本之间非线性的响应关系,最后,利用蒙特卡洛法预测地铁基坑的失效概率。结合实例分析表明,该方法计算效率高且结果合理,为地铁基坑工程风险分析提供了一个有效的途径。
The traditional analysis method of foundation pit engineering reliability has large error and calculation amount.In order to solve the above problems,this paper introduces the support vector machine algorithm and combines with the uniform experiment to establish a subway foundation pit risk analysis method based on the support vector machine response surface.The uniformity test is used to construct the learning samples,and the vector machine is used to learn the samples,so as to establish the nonlinear response relationship between the samples.Finally,the Monte Carlo method is used to predict the failure probability of the subway foundation pit.Combined with case analysis,the method has high computational efficiency and reasonable results and provides an effective way for risk analysis of subway foundation pit engineering.
作者
解继超
肖盛莲
XIE Ji-chao;XIAO Sheng-lian(Sichuan College of Architectural Technology,Deyang 618000,China)
出处
《价值工程》
2018年第35期167-169,共3页
Value Engineering
关键词
地铁基坑
风险
支持向量机
均匀试验
蒙特卡洛法
subway foundation pit
risk
support vector machine
uniform experiment
Monte Carlo method
