水力发电2017，Vol.43Issue(7)：37-40,4.
基于EEMD的BP神经网络边坡预测研究
Research on Side Slope Prediction Using BP Neural Network Based on EEMD
摘要
Abstract
A new algorithn (EEMD-BP) based on Ensemble Empirical Mode Decomposition (EEMD) and BP neural network is proposed to solve the problem of nonstationary and nonlinear data processing in slope deformation.The algorithm firstly decomposes the deformation sequence of slope by EEMD which can effectively separate the subsequence with different scale features in time series,and then establishes BP neural network prediction models for each sub-sequence,and finally,the final deformation prediction resuh can be obtained by the superimposing of each sub-sequence prediction results.The results comparison between this algorithm and GM(1,1) and BP neural network model show that the algorithm has high prediction accuracy and can guarantee better local prediction value in the period when the slope fluctuation fluctuates violently.关键词
边坡/变形/预测/EEMD-BP模型Key words
slope/deformation/prediction/EEMD-BP model分类
建筑与水利引用本文复制引用
晏红波,杨庆,任超,毕旋旋..基于EEMD的BP神经网络边坡预测研究[J].水力发电,2017,43(7):37-40,4.基金项目
广西自然科学基金项目(2016GXNSFAA380013) （2016GXNSFAA380013）
广西“八桂学者”岗位专项经费资助项目,广西空间信息与测绘重点实验室资助课题(桂科能130511409,130511415,15-140-07-17,15-140-07-18,16-380-25-03,16-380-25-16) （桂科能130511409,130511415,15-140-07-17,15-140-07-18,16-380-25-03,16-380-25-16）
