Title :
Modeling dynamics of large belt conveyor system based on least square support vector machine
Author :
Wei, Chen ; Xin, Li
Author_Institution :
Sch. of Electr. Eng. & Autom., Hefei Univ. of Technol., Hefei, China
Abstract :
Considering nonlinear, severe disturbance and time-varying characteristics of large belt conveyor system, the nonlinear mechanism model is analyzed in the paper. The sample data set is obtained from the experimental belt conveyor system by the finite elements method, and the predictive model of belt conveyor system based on the least square support vector machine is built up to improve the prediction accuracy and decrease the prediction time. Compared with the models based on nonlinear regression analysis method, the simulation results are shown that the model based on LS-SVM algorithm is superior to nonlinear regression analysis in data fitting.
Keywords :
belts; conveyors; least squares approximations; nonlinear systems; regression analysis; support vector machines; time-varying systems; LS-SVM algorithm; data fitting; finite elements method; large belt conveyor system; least square support vector machine; modeling dynamics; nonlinear characteristics; nonlinear mechanism model; prediction accuracy; prediction time; predictive model; regression analysis method; sample data set; time-varying characteristics; Analytical models; Belts; Data models; Educational institutions; Electronic mail; Regression analysis; Support vector machines; belt conveyor system; kernel function; least square support vector machine; modeling;
Conference_Titel :
Control Conference (CCC), 2012 31st Chinese
Conference_Location :
Hefei
Print_ISBN :
978-1-4673-2581-3
