【摘要】 为同时利用不同大坝变形预测方法的特征信息,改进预测质量,提出了一种基于微粒群优化—支持向量机(PSO-SVM)的大坝变形非线性智能组合预测模型。选取几种不同原理的建模方法建立预测模型并预测,利用其预测结果建立组合预测模型,组合函数的拟合采用混合核函数支持向量回归算法。为提高SVM的学习、泛化能力,采用混合核函数,并用具有并行性和分布式特点的PSO算法优化选择SVM模型参数。实例分析表明,该模型较好地整合了不同建模方法的特征信息,避免了单一方法的偶然性,较单一预测模型、加权组合预测模型具有更高的预测精度和更小的峰值误差,为更准确地进行大坝安全监控提供了一种新的途径。更多还原

【Abstract】 In order to use the characteristic information of different modeling methods sufficiently and improve the quality of prediction result,a nonlinear combining forecasting model for dam deformation forecasting based on support vector machines with particle swarm optimization was presented in this paper.Firstly,predicting the prediction variable separately by several different modeling methods,then the nonlinear agent combined forecasting model was built using the prediction results,and the combinatorial function was got through support vector machines.In the interest of improving the forecasting accuracy,support vector machines which using a mixed kernel function was used,and the parameters of SVM were selected by PSO algorithm which had the characteristics of parallel and distributing.The new model is used to dam deformation modeling and forecasting,result show that the model combine the characteristic information of different modeling methods very well.Comparing with single predicting model and regressive combining model,the PSO-SVM combining model has the highest prediction precision and the smallest peak error,thus a new approach for dam safety monitoring is provided.更多还原