Modeling and simulation of wind turbine Savonius rotors using artificial neural networks for estimation of the power ratio and torque |
| |
| Authors: | J. Sargolzaei A. Kianifar |
| |
| Affiliation: | 1. Department of Chemical Engineering, Ferdowsi University of Mashhad, P.O. Box 9177948944, Mashhad, Iran;2. Department of Mechanical Engineering, Ferdowsi University of Mashhad, P.O. Box 9177948944, Mashhad, Iran;1. Faculty of Engineering, Mechanical Engineering Department, Urmia University, Urmia, Iran;2. Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran;3. Renewable Energy Lab., Faculty of Engineering-Mattaria, Helwan University, Cairo, Egypt;4. Mechanical Engineering Dept., College of Engineering and Islamic Architecture, Umm Al-Qura University, P.O. 5555, Makkah, Saudi Arabia;1. Arista Renewable Energies, 2648 Av. Desjardins, Montréal, Québec, Canada;2. École de technologie supérieure, 1100 Notre-Dame Ouest, Montréal, Québec, Canada;1. Renewable Energy Research Group, Department of Building Services Engineering, The Hong Kong Polytechnic University, Hong Kong;2. Department of Power Engineering, North China Electric Power University (Baoding), Baoding, PR China;3. School of Energy and Power Engineering, University of Shanghai for Science and Technology, PR China;1. School of Marine Science and Technology, Northwestern Polytechnical University, Xi''an 710072, China;2. Key Laboratory for Unmanned Underwater Vehicle, Northwestern Polytechnical University, Xi''an 710072, China;3. Harbor Branch Oceanographic Institute, Florida Atlantic University, Fort Pierce, FL 34946, USA |
| |
| Abstract: | The power factor and torque of wind turbines are predicted using artificial neural networks (ANNs) based on experimental data which have been collected for seven prototype vertical Savonius rotors tested in a wind tunnel. In this research, the rotors with different configurations were located in the wind tunnel and the tests were repeated 4–6 times in order to reduce errors. Since the Reynolds number has a negligible effect on power ratio, therefore tip speed ratio (TSR) is the main input parameter to be predicted in neural network. Also, the rotor’s power factor and torque were simulated for different tip speed ratios and different blade angles. The simulated results show a strong capability for providing reasonable predictions and estimations of the maximum power of rotors and maximizing the efficiency of Savonius turbines. According to artificial neural nets simulations and the experimental results, increasing tip speed ratio leads to a higher power ratio and torque. For all the tested rotors, a maximum and minimum amount of torque has happened at angle of 60o and 120o, respectively. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
