Author:
Du Sunwen,Song Ruiting,Qu Qing,Zhao Zhiying,Sun Hailing,Chen Yanwei
Abstract
At present, due to the complex and changeable geological conditions, the precise deformation prediction technology of high and steep slope could not achieve an accurate prediction. In particular, the single forecasting model has some problems such as poor stability, low precision, and data fluctuation. In practice, excavating the complex nonlinear relationship between open-pit slope surface deformation monitoring data and various influencing factors and improving the accuracy of the deformation prediction of high and steep slopes is the key to safe open-pit mine production. It proposed to introduce the position factor and the velocity factor into a twin support vector machine (TWSVM). The adaptive subgroup optimisation (APSO) algorithm is selected for parameter optimisation. Through the comparative analysis of TWSVM, genetic algorithm-TWSVM (GA-TWSVM), and the proposed APSO⁃TWSVM, the experimental data show that the mean absolute error (MAE) values of the three models are 13.29 %,8.17 %, and 1.27 %, the RMSE - 47.83 %,6.52 %, and 3.02 %, respectively; the prediction time for APSO⁃TWSVM is improved by 62.5 % compared to GA-TWSVM.
Publisher
Kaunas University of Technology (KTU)
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献