基于偏最小二乘回归和最小二乘支持向量机的大坝渗流监控模型

利用偏最小二乘回归法对影响大坝渗流的诸多因素进行分析,提取对因变量影响强的成分,克服了变量间的多重相关性问题,降低了最小二乘支持向量机的输入维数,从而可以较好的解决非线性问题,建立了基于PLS-LSSVM的大坝渗流监控模型。实例分析表明,PLS-LSSVM模型的拟合与预测精度均优于独立使用PLS或LSSVM建模的精度;PLS-LSSVM模型的学习训练效率比LSSVM模型有较大的优势,更适合于大规模的数据建模。

Monitoring model for dam seepage based on partial least squares regression and partial least square support vector machine

The partial least-squares regression method is applied to analyzed the factors affecting the dam seepage to extract the most important components.So that the problem of nultiple correlations can be solved and the number of input dimensions of least square support vector machine can be reduced to avoid the nonlinear problem happened to the application of least square support vector machine.On this basis,a monitoring model for dam seepage based on the combination of partial least-squares regression method with partial least square support vector machine is established.The application example shows that this model has higher precision and higher training efficiency than the models based on partial least-squares regression or partial least square support vectors machine alone.