论文部分内容阅读
深基坑变形预测一直是深基坑工程的一个重点研究课题,具有十分重要的理论意义和实际价值。支持向量机是一种基于结构风险最小化原理的机器学习算法,它具有很好的泛化能力,能够有效地解决小样本、非线性、高维数、局部极小等问题。本文将支持向量机(SVM)理论引入到深基坑的变形预测当中,同时,采用粒子群算法(PSO)来优化SVM的相关参数,将其预测结果与传统的支持向量机模型和BP神经网络模型的预测结果进行对比。结果表明,PSO-SVM模型用于变形预测是可行的。
Deep excavation deformation prediction has been a key research project of deep foundation pit engineering, which has very important theoretical and practical values. SVM is a machine learning algorithm based on the principle of structural risk minimization. It has good generalization ability and can effectively solve the problems of small sample, nonlinearity, high dimension and local minima. In this paper, the support vector machine (SVM) theory is introduced into the deformation prediction of deep foundation pit. At the same time, particle swarm optimization (PSO) is used to optimize the related parameters of SVM, and its prediction results are compared with the traditional support vector machine model and BP neural network The model predictions are compared. The results show that PSO-SVM model is feasible for deformation prediction.