支持向量机在边坡稳定分析预测的应用

发布时间：2018-02-26 00:09

本文关键词： 边坡稳定粒子群算法支持向量机预测　出处：《沈阳建筑大学学报(自然科学版)》2017年06期 　论文类型：期刊论文

【摘要】：目的提出一种基于改进算法的支持向量机模型(PSO-SVM),利用边坡的参数分析预测边坡稳定性.方法利用支持向量机有效解决小样本、高维数、非线性等问题的优势,建立粒子群算法(PSO)优化的支持向量机模型,粒子群算法优化支持向量机参数,模型中边坡几何参数和强度参数:边坡角β、边坡高度H、岩石容重γ、黏聚力c、内摩擦角φ以及孔隙水压力ru作为输入参数,边坡稳定性系数FS和边坡稳定状态S作为输出参数.结果 PSO-SVM模型与网格搜索算法(GS)、遗传算法(GA)优化SVM模型以及人工神经网络ANN模型相比,具有更高的分类精度和更强的预测能力.结论 PSO-SVM模型能够准确地获得边坡的稳定性系数,评价其稳定性,在边坡稳定分析和预测中具有良好的实际应用价值.
[Abstract]:Aim to propose a new support vector machine model based on improved algorithm, which can be used to analyze and predict slope stability by using the parameters of slope. Methods support vector machine is used to solve the problems of small sample size, high dimension, nonlinearity and so on. The support vector machine (SVM) model of particle swarm optimization (PSO) optimization is established, and the PSO algorithm is used to optimize the support vector machine (SVM) parameters. In the model, the geometric and strength parameters of the slope are as follows: slope angle 尾, slope height H, rock bulk density 纬, cohesive force c, internal friction angle 蠁 and pore water pressure r u as input parameters. The slope stability coefficient FS and slope stability state S are the output parameters. Results the PSO-SVM model is compared with the grid search algorithm, the genetic algorithm (GA) to optimize the SVM model and the artificial neural network (ANN) model. Conclusion the PSO-SVM model can accurately obtain the slope stability coefficient and evaluate its stability, which has a good practical application value in slope stability analysis and prediction.
【作者单位】：西安建筑科技大学材料与矿资学院;西安建筑科技大学土木工程学院;西安科技大学能源学院;
【基金】：国家自然科学基金项目(10772143) 陕西省科技统筹项目(2015TZC-G-8-9)
【分类号】：TU43

【相似文献】