Application of Extreme Learning Machine Combination Model for Dam Displacement Prediction

作者：Cheng Jiatang^*; Xiong Yan

来源：7th International Congress of Information and Communication Technology (ICICT), 2017-01-01 To 2017-01-02.

DOI：10.1016/j.procs.2017.03.120

• dam
• displacement
• combination prediction
• extreme learning machine

The dam displacement can effectively reflect the dam security status. To improve the accuracy of dam displacement prediction, a combination prediction model is presented based on extreme learning machine (ELM). In this combination model, the predictive values of the grey GM(1,1) and regression analysis, combined with the average values of predictive results of the two methods, are used as the input vectors of ELM, and the actual values of dam displacement are selected as the output vectors, and then the nonlinear combination prediction model is built. The simulation results show that the mean relative error, the average absolute error are 3.04% and 4.14% of the combination method based on extreme learning machine, respectively, which less than those of the GM(1,1), regression analysis and equal weight combination method, and is suitable for the prediction of dam displacement.

• 出版日期2017
• 单位红河学院