Dam deformation prediction model based on empirical mode decomposition and LM-BP neural network
Fang Xu-hua · Fuzhou daxue xuebao. Ziran kexue ban · 2011
A novel model based on empirical mode decomposition(EMD) and neural network for dam deformation prediction is presented in the paper.Firstly,considering that EMD has an advantage to do adaptive decomposition according to characteristics of the signal itself,deformation time series is decomposed into a series of intrinsic mode functions(IMF) in different scale space.Then,according to the change regulation of each IMF,they are forecasted by appropriate LM-BP neural networks.Finally,these forecasting results of each IMF are combined to obtain final forecasting result.The calculation result of a practical example shows that this model has higher forecasting precision and better adaptability.