%0 Journal Article
%A CAO En-hua
%A BAO Teng-fei
%A HU Shao-pei
%A YUAN Rong-yao
%A YAN Tao
%T A Deformation Prediction Model for Concrete Dam Based on Extreme Learning Machine Optimized by Variable Selection
%D 2022
%R 10.11988/ckyyb.20210276
%J Journal of Changjiang River Scientific Research Institute
%P 59-65
%V 39
%N 7
%X Traditional statistical models are of weak generalization capability and are prone to introduce high-dimensional variables,which will negatively affect the output of neural network-based prediction models and increase the risk of overfitting.It is necessary to build a data-driven model with appropriate dimensionality to accomplish accurate monitoring of dam deformation.In this paper,extreme learning machine(ELM)is selected as the base prediction model,and a variable selection method based on mean impact value(MIV)-ELM model is proposed to eliminate redundant information in the initial variable set,thus reducing the model's complexity and improving the prediction accuracy.Analysis results demonstrate that compared with traditional prediction models,HST-MIV-ELM not only has the highest prediction accuracy and robustness,but also has strong scalability.The study provides a reliable theoretical basis for the construction of dam safety monitoring system.
%U http://ckyyb.crsri.cn/EN/10.11988/ckyyb.20210276