Abstract：For the problem of mode confusion in the implementation of the local mean decomposition, this paper analyzed the theory of LMD and least squares support vector regression, and proposed the forecasting model of dam deformation named ELMD-LSSVM. With the ELMD method, the deformation sequence is decomposed and then each subsequence is forecasted with LSSVM. After reconstruction, the forecasted results are obtained. Experimental results of two models show that the ELMD-LSSVM model is better than other models. It is able to overcome the problem of mode mixing and perform dam deformation in different feature scales simultaneously with those characteristics. So the ELMD-LSSVM model is very suitable to be applied to the dam deformation analysis and prediction of the deformation object.
王奉伟，周昀琦，周世健，罗亦泳. 大坝变形多尺度分析ELMD-LSSVM预测模型[J]. 辽宁工程技术大学学报(自然科学版), 2016, 35(12): 1475-1479.
WANG Fengwei, ZHOU Yunqi, ZHOU Shijian, LUO Yiyong. Forecasting model of dam deformation based on ELMD-LSSVM method. Journal of LNTU.Natural Science, 2016, 35(12): 1475-1479.