Support vector regression methodology for wind turbine reaction torque prediction with power-split hydrostatic continuous variable transmission
| Autor: | Miss Laiha Mat Kiah, Shahaboddin Shamshirband, Dalibor Petković, Vlastimir Nikolić, Abdullah Gani, Amineh Amini, Žarko Ćojbašić, Nor Badrul Anuar |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Engineering
Wind power business.industry Mechanical Engineering Building and Construction Pollution Turbine Industrial and Manufacturing Engineering Wind speed Renewable energy Power (physics) Support vector machine General Energy Control theory Torque Electrical and Electronic Engineering business Civil and Structural Engineering Continuously variable transmission |
| Zdroj: | Energy. 67:623-630 |
| ISSN: | 0360-5442 |
| Popis: | Nowadays the use of renewable energy including wind energy has risen dramatically. Because of the increasing development of wind power production, improvement of the prediction of wind turbine output energy using classical or intelligent methods is necessary. To optimize the power produced in a wind turbine, speed of the turbine should vary with wind speed. Variable speed operation of wind turbines presents certain advantages over constant speed operation. This paper has investigated power-split hydrostatic continuously variable transmission (CVT). The objective of this article was to capture maximum energy from the wind by prediction the optimal values of the wind turbine reaction torque. To build an effective prediction model, the polynomial and radial basis function (RBF) are applied as the kernel function of Support Vector Regression (SVR) for prediction of wind turbine reaction torque in this research study. Instead of minimizing the observed training error, SVR_poly and SVR_rbf attempt to minimize the generalization error bound so as to achieve generalized performance. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by our proposed approach. Results show that SVRs can serve as a promising alternative for existing prediction models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect