Publication: Wind turbine power coefficient models based on neural networks and polynomial fitting
dc.affiliation.dpto | UC3M. Departamento de Ingeniería Eléctrica | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Redes y Sistemas de Energía Eléctrica (REDES) | es |
dc.contributor.author | Carpintero Rentería, Miguel | |
dc.contributor.author | Santos Martín, David | |
dc.contributor.author | Lent, Andrew | |
dc.contributor.author | Ramos González, Carlos | |
dc.date.accessioned | 2022-05-03T12:40:17Z | |
dc.date.available | 2022-05-03T12:40:17Z | |
dc.date.issued | 2020-08-01 | |
dc.description.abstract | The power coefficient parameter represents the aerodynamic wind turbine efficiency. Since the 1980s, several equations have been used in the literature to study the power coefficient as a function of the tip speed ratio and the pitch angle. In this study, these equations are reviewed and compared. A corrected blade element momentum algorithm is used to generate three sets of data representing different ranges of wind turbines, going from 2 to 10 MW. With this information, two power coefficient models are proposed and shared. One model is based on a polynomial fitting, whereas the other is based on neural network techniques. Both were trained with the blade element momentum model output data and showed good behaviour for all operating ranges. In the results, compared to all the algorithms found in the literature, the proposed models reduced the power coefficient error by at least 55% compared to the best numerical approximation from the literature. An error reduction in the power coefficient parameter may have a large impact on many wind energy conversion system studies, such as those treating dynamic and transient behaviours | en |
dc.description.status | Publicado | es |
dc.format.extent | 8 | |
dc.identifier.bibliographicCitation | IET Renewable Power Generation, (2020), 14(11), pp.: 1841-1849. | en |
dc.identifier.doi | https://doi.org/10.1049/iet-rpg.2019.1162 | |
dc.identifier.issn | 1752-1416 | |
dc.identifier.publicationfirstpage | 1841 | |
dc.identifier.publicationissue | 11 | |
dc.identifier.publicationlastpage | 1849 | |
dc.identifier.publicationtitle | IET Renewable Power Generation | en |
dc.identifier.publicationvolume | 14 | |
dc.identifier.uri | https://hdl.handle.net/10016/34672 | |
dc.identifier.uxxi | AR/0000027421 | |
dc.language.iso | eng | en |
dc.publisher | Institution of Engineering and Technology | en |
dc.rights | © The Institution of Engineering and Technology 2020 | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Ingeniería Industrial | es |
dc.subject.other | Blades | en |
dc.subject.other | Aerodynamics | en |
dc.subject.other | Wind turbines | en |
dc.subject.other | Polynomial approximation | en |
dc.subject.other | Neural nets | en |
dc.subject.other | Curve fitting | en |
dc.subject.other | Mechanical engineering computing | en |
dc.title | Wind turbine power coefficient models based on neural networks and polynomial fitting | en |
dc.type | research article | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1