基于改进支持向量机的深基坑变形预测

发布时间：2017-12-27 09:39

本文关键词：基于改进支持向量机的深基坑变形预测　出处：《地矿测绘》2015年04期 　论文类型：期刊论文

【摘要】：深基坑变形监测与预测是深基坑设计施工中的一个重要的环节,准确地预测深基坑未来的变形,是深基坑变形监测的最终目的。针对传统常用预测方法存在一定的局限性这个问题,结合支持向量机的研究现状,提出将能够有效地解决小样本、非线性、高维数、局部极小等问题的支持向量机模型应用于深基坑变形预测的方法。具体方法是:采用粒子群算法对支持向量机的相关参数进行寻优,得到改进支持向量机预测模型,然后将其预测结果与传统的支持向量机模型、Elman动态神经网络模型预测结果进行比较,最后采用均方误差、平方和误差、平均相对误差对预测效果进行评价。实验结果表明,基于改进支持向量机预测模型用于变形预测是可行的,且能更好地反映深基坑系统的动态非线性特点,具有一定的优越性与工程应用推广价值。
[Abstract]:The deformation monitoring and prediction of deep foundation pit is an important link in the design and construction of deep foundation pit. Accurately predicting the future deformation of deep foundation pit is the ultimate goal of deep foundation pit deformation monitoring. According to the traditional prediction method of this problem exists some limitations, combined with the research status of support vector machine, the proposed method using support vector machine model can effectively solve the small sample, nonlinear, high dimension and local minima in the deep foundation pit deformation prediction. The specific method is: using particle swarm algorithm to optimize the parameters of support vector machine, improved prediction model of support vector machine, and then the prediction results with the traditional support vector machine model, Elman neural network model prediction results are compared, finally using the mean square error, and square error, average relative error to evaluate the effect of prediction. The experimental results show that the improved support vector machine prediction model is feasible for deformation prediction, and it can better reflect the dynamic nonlinear characteristics of deep foundation pit system. It has certain superiority and popularization value in engineering application.
【作者单位】：江西环境工程职业学院;江西省水土保持科学研究院;江西省煤田地质局测绘大队;
【分类号】：TU433
【正文快照】： 0引言变形(Deformation)是指在各种影响因素的作用下,变形体的大小、形状、位置在时空域中的变化,是自然界普遍存在的现象[1]。当变形体的变形不超过一定允许的范围内,是不会造成危害的,但若超过这个允许值,则可能引发灾害,如地震、采矿塌陷、坝内蜂窝、火山爆发、滑坡、桥梁

【相似文献】