基于集合经验模态分解和支持向量机的大坝变形预测方法

Dam Deformation Prediction Method Based on Ensemble Empirical Mode Decomposition and Support Vector Machine

受水位、温度等诸多因素共同影响,大坝变形具有随机性和非线性特征,提出了一种基于集合经验模态分解(EEMD)和支持向量机(SVM)的大坝变形预测算法。算法先对大坝位移序列进行集合经验模态分解,有效分离出隐含在时序中的非线性高频波动成分和低频趋势成分;其次根据各分量特点构造不同的SVM进行预测,最后叠加各分量预测值得到预测结果。与BP神经网络模型及传统支持向量机的对比结果表明,所提预测算法具有较强的自适应预测能力,预测精度较高。

Affected by water level, temperature and other factors, the deformation of dam is random and nonlinear. A new algorithm based on Ensemble Empirical Mode Decomposition （EEMD） and Support Vector Machine （SVM） for dam deformation prediction is presented herein. First, the deformation sequence is decomposed by EEMD in order to effectively separate the nonlinear trend of high frequency component volatility and low frequency component. Then, the SVM is applied to build a prediction model for each component. Finally, the predicted values of each component are superimposed. The calculation result is analyzed and compared with the results of BP neural network and traditional SVM. The comparison shows that the new algorithm has stronger ability of adaptive fitting prediction and the prediction accuracy is higher.