基于SCE-UA/SVM的大坝变形预测模型研究

Research on Dam Deformation Prediction Model Based on SVM Combined with SCE-UA Algorithm

为提高大坝变形预测模型的精度,采用复合形交叉进化算法(SCE-UA),以均方根差最小为目标来优化支持向量机(SVM)的参数,从而建立了基于SCE-UA/SVM的大坝变形预测模型,并结合实际监测数据,对比分析了该模型与统计模型的优劣。结果表明,该模型能够提高大坝变形的预测精度,为大坝变形预测提供了一种新的思路。

With the purpose of improving prediction precision,a new dam deformation prediction model based on SCE-UA/SVM was established in this work.The algorithm,shuffled complex evolution method developed at the University of Arizona（SCE-UA）,was adopted to optimize the parameters of support vector machine（SVM）with minimum root mean square error as target function.Based on actual monitoring data,the capability of this model and statistical model was compared.The results show that the proposed model is able to improve prediction precision,which provides a new method for dam deformation prediction.