Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Application of Optimized Parameters SVM in Deformation Prediction of Creep Landslide Tunnel
Creep landslide tunnel deformation is a diversity,changeability, less information, complicated nonlinear problem, it’s unable to establish accurate mathematical model.A creep landslide tunnel deformation prediction model based on SVM was constructed in this paper to enhance prediction accuracy, and penalty parameter c and Kernel function parameter g of SVM were optimized by genetic algorithms (GA).nine closely related factors in creep landslide tunnel deformation were selected as Input vector of SVM , creep landslide tunnel deformation measured value as a model target output. In Matlab 2011b simulation software,80 groups observation data from 2012 to 2013 of Laoyeling tunnel in Changchun to Hunchun highway of Jilin province as the sample data, 70 groups were used as training set, other 10 groups were used as testing set. The simulation result shows that testing value is very close to the true value in this method, the average relative error close to 2%. Effectiveness of the creep landslide tunnel deformation prediction based on GA_SVM model is verified by experiments.
Application of Optimized Parameters SVM in Deformation Prediction of Creep Landslide Tunnel
Creep landslide tunnel deformation is a diversity,changeability, less information, complicated nonlinear problem, it’s unable to establish accurate mathematical model.A creep landslide tunnel deformation prediction model based on SVM was constructed in this paper to enhance prediction accuracy, and penalty parameter c and Kernel function parameter g of SVM were optimized by genetic algorithms (GA).nine closely related factors in creep landslide tunnel deformation were selected as Input vector of SVM , creep landslide tunnel deformation measured value as a model target output. In Matlab 2011b simulation software,80 groups observation data from 2012 to 2013 of Laoyeling tunnel in Changchun to Hunchun highway of Jilin province as the sample data, 70 groups were used as training set, other 10 groups were used as testing set. The simulation result shows that testing value is very close to the true value in this method, the average relative error close to 2%. Effectiveness of the creep landslide tunnel deformation prediction based on GA_SVM model is verified by experiments.
Application of Optimized Parameters SVM in Deformation Prediction of Creep Landslide Tunnel
Applied Mechanics and Materials ; 675-677 ; 265-268
08.10.2014
4 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Method for constructing anti-slide piles in creep deformation landslide mass
| Europäisches Patentamt | 2020
Creep model of Kanto loam and its application to time prediction of landslide
| British Library Conference Proceedings | 1996
Application of Fuzzy Least Squares Support Vector Machines in Landslide Deformation Prediction
| British Library Conference Proceedings | 2012
| DOAJ | 2022