Pasar al contenido principal

ANALISIS Y CONTROL DE UN DISPOSITIVO FLOTANTE HIBRIDO DE ENERGIA EOLICA Y MARINA

RTI2018-094902-B-C21

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD COMPLUTENSE DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Redes neuronales y aprendizaje por refuerzo en el control de turbinas eólicas, Neural networks and reinforcement learning in wind turbine control

  • Sierra-García, J. E.
  • Santos, M.
[EN] Pitch control of wind turbines is complex due to the intrinsic non-linear behavior of these devices, and the external disturbances they are subjected to related to changing wind conditions and other meteorological phenomena. This difficulty is even higher in the case of floating offshore turbines, due to ocean currents and waves. Neural networks and other intelligent control techniques have been proven very useful for the modeling and control of these complex systems. Thus, this paper presents different intelligent control configurations applied to wind turbine pitch control. Direct pitch control based on neural networks and reinforcement learning, and some hybrid control configurations are described. The usefulness of neuro-estimators for the improvement of controllers is also presented. Finally, some of these techniques are used in an application example with a land wind turbine model., [ES] El control del ángulo de las palas de las turbinas eólicas es complejo debido al comportamiento no lineal de los aerogeneradores, y a las perturbaciones externas a las que están sometidas debido a las condiciones cambiantes del viento y otros fenómenos meteorológicos. Esta dificultad se agrava en el caso de las turbinas flotantes marinas, donde también les afectan las corrientes marinas y las olas. Las redes neuronales, y otras técnicas del control inteligente, han demostrado ser muy útiles para el modelado y control de estos sistemas. En este trabajo se presentan diferentes configuraciones de control inteligente, basadas principalmente en redes neuronales y aprendizaje por refuerzo, aplicadas al control de las turbinas eólicas. Se describe el control directo del ángulo de las palas del aerogenerador y algunas configuraciones híbridas de control. Se expone la utilidad de los neuro-estimadores para la mejora de los controladores. Finalmente, se muestra un ejemplo de aplicación de algunas de estas técnicas en un modelo de turbina terrestre., Ministerio de Ciencia, Innovación y Universidades: Proyecto MCI AEI/FEDER RTI2018- 094902-B-C21
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Estabilización de eólica marina flotante mediante control de flujo de aire en columnas de agua oscilante, Airflow Control Strategy of Oscillating Water Columns for Floating Offshore Wind Turbine Stabilization

  • M’zoughi, Fares
  • Aboutalebi, Payam
  • Garrido, Izaskun
  • Garrido, Aitor J.
  • Sen, Manuel de la
[Resumen] En este artículo se presenta un nuevo tipo de control aplicado a una plataforma flotante multipropósito tipo barcaza capaz de aprovechar la energía eólica y undimotriz de manera simultánea. Además, los captadores de energía undimotriz se componen de columnas de agua oscilante (OWC) que ayudarán a estabilizar la plataforma y la turbina eólica flotante (FOWT) reduciendo el desplazamiento longitudinal de la parte superior de la torre. Para ello se implementa una estrategia de control de flujo de aire actuando sobre las válvulas de la cámara de captura de los dispositivos OWC. El estudio comparativo entre una FOWT estándar y la FOWT sobre la plataforma dotada de dispositivos controlados OWC propuesta, muestra una considerable mejora en la estabilidad del sistema., [Abstract] This paper presents the idea of incorporating oscillating water columns (OWCs) into the barge platform of a floating offshore wind turbines (FOWT) to make it a multi-purpose platform for harnessing both wind and wave energies. Moreover, the OWCs will help stabilize the FOWT platform by means of an airflow control strategy used to reduce the platform pitch and tower top fore-aft displacement. This is achieved by a proposed airflow control strategy to control the valves within the OWCs. The comparative study between a standard FOWT and the proposed OWC-based FOWT shows an improvement in the platform’s stability., Gobierno Vasco; IT1207-19, Este trabajo ha sido apoyado en parte por el Gobierno Vasco a través del proyecto IT1207-19 y por el MCIU/MINECO a través de los proyectos RTI2018-094902-B-C21 y RTI2018-094902-B-C22 (MCIU / AEI / FEDER, UE), https://doi.org/10.17979/spudc.9788497498043
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Nueva estrategia de control para la reducción de oscilaciones en turbinas eólicas flotantes, A Novel Control Strategy for Oscillation Reduction in Floating Wind Turbines

  • Aboutalebi, Payam
  • M’zoughi, Fares
  • Garrido, Izaskun
  • Garrido, Aitor J.
[Resumen] En este trabajo se ha propuesto una nueva estrategia de control para mejorar la estabilidad de turbinas eólicas flotantes (FWT). Al objeto de estudiar la reducción de oscilaciones no deseadas en el sistema, y en particular en los movimientos de cabeceo de la plataforma y de proa-popa de la nacelle, se ha considerado una plataforma tipo barcaza de forma cuadrada y equipada con cuatro columnas de agua oscilantes (OWC) colocadas de manera simétrica. De esta forma, las válvulas de control de flujo de aire de las cámaras de captura permiten operar las citadas columnas de aire para controlar los movimientos de la barcaza causados por la dinámica oscilatoria de la ola incidente. Para ello, se ha efectuado un análisis de los operadores de amplitud de respuesta (RAO) que permite implementar una nueva estrategia de control de conmutación para regular adecuadamente la transición apertura/cierre de las válvulas de control de flujo. Los resultados obtenidos muestran que la topología de plataforma híbrida propuesta, dotada de sistemas controlados OWC, presenta un mejor rendimiento que una plataforma análoga tradicional., [Abstract] In this work, a new control strategy has been proposed to improve the stability of floating wind turbines (FWT). In order to study the reduction of undesired oscillations in the system, and in particular in the platform pitch and fore-aft nacelle movements. A square-shaped barge-type platform has been considered and equipped with four symmetrically located Oscillating Water Columns (OWCs). In this way, the air flow control valves of the capture chambers allow the aforementioned air columns to be operated so that to control the movements of the barge caused by the oscillatory dynamics of the incident wave. To do so, an analysis of the response amplitude operators (RAO) has been carried out, which in turn allows the implementation of a new switching control strategy to properly regulate the transition of the flow control valves. The results obtained show that the proposed hybrid platform topology, equipped with OWC controlled systems, presents better performance than a traditional analog platform., Gobierno Vasco; IT1207-19, Los autores del presente trabajo quisieran agradecer el apoyo del Gobierno Vasco mediante el proyecto IT1207-19 y del MCIU/MINECO a través de los proyectos RTI2018-094902-B-C21 y RTI2018-094902-B-C22 (MCIU/AEI/FEDER, UE), https://doi.org/10.17979/spudc.9788497498043
Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Artículo científico (JournalArticle)

Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control

  • Sierra Garcia, Jesús Enrique
  • Santos, Matilde
This work focuses on the control of the pitch angle of wind turbines. This is not an easy task due to the nonlinearity, the complex dynamics, and the coupling between the variables of these renewable energy systems. This control is even harder for floating offshore wind turbines, as they are subjected to extreme weather conditions and the disturbances of the waves. To solve it, we propose a hybrid system that combines fuzzy logic and deep learning. Deep learning techniques are used to estimate the current wind and to forecast the future wind. Estimation and forecasting are combined to obtain the effective wind which feeds the fuzzy controller. Simulation results show how including the effective wind improves the performance of the intelligent controller for different disturbances. For low and medium wind speeds, an improvement of 21% is obtained respect to the PID controller, and 7% respect to the standard fuzzy controller. In addition, an intensive analysis has been carried out on the influence of the deep learning configuration parameters in the training of the hybrid control system. It is shown how increasing the number of hidden units improves the training. However, increasing the number of cells while keeping the total number of hidden units decelerates the training., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was partially supported by the Spanish Ministry of Science, Innovation and Universities under MCI/AEI/FEDER Project Number RTI2018-094902-B-C21., Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE
Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Artículo científico (JournalArticle)

Wind turbine pitch reinforcement learning control improved by PID regulator and learning observer

  • Sierra Garcia, Jesús Enrique
  • Santos, Matilde
  • Pandit, Ravi
Wind turbine (WT) pitch control is a challenging issue due to the non-linearities of the wind device and its complex dynamics, the coupling of the variables and the uncertainty of the environment. Reinforcement learn- ing (RL) based control arises as a promising technique to address these problems. However, its applicability is still limited due to the slowness of the learning process. To help alleviate this drawback, in this work we present a hybrid RL-based control that combines a RL-based controller with a proportional–integral–derivative (PID) regulator, and a learning observer. The PID is beneficial during the first training episodes as the RL based control does not have any experience to learn from. The learning observer oversees the learning process by adjusting the exploration rate and the exploration window in order to reduce the oscillations during the training and improve convergence. Simulation experiments on a small real WT show how the learning significantly improves with this control architecture, speeding up the learning convergence up to 37%, and increasing the efficiency of the intelligent control strategy. The best hybrid controller reduces the error of the output power by around 41% regarding a PID regulator. Moreover, the proposed intelligent hybrid control configuration has proved more efficient than a fuzzy controller and a neuro-control strategy., This work was partially supported by the Spanish Ministry of Sci- ence, Innovation and Universities under MCI/AEI/FEDER Project num- ber RTI2018-094902-B-C21.
Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Artículo científico (JournalArticle)

Hybrid Optimized Fuzzy Pitch Controller of a Floating Wind Turbine with Fatigue Analysis

  • Serrano, Carlos
  • Sierra Garcia, Jesús Enrique
  • Santos, Matilde
Floating offshore wind turbines (FOWTs) are systems with complex and highly nonlinear dynamics; they are subjected to heavy loads, making control with classical strategies a challenge. In addition, they experience vibrations due to wind and waves. Furthermore, the control of the blade angle itself may generate vibrations. To address this issue, in this work we propose the design of an intelligent control system based on fuzzy logic to maintain the rated power of an FOWT while reducing the vibrations. A gain scheduling incremental proportional–derivative fuzzy controller is tuned by genetic algorithms (GAs) and combined with a fuzzy-lookup table to generate the pitch reference. The control gains optimized by the GA are stored in a database to ensure a proper operation for different wind and wave conditions. The software Matlab/Simulink and the simulation tool FAST are used. The latter simulates the nonlinear dynamics of a real 5 MW barge-type FOWT with irregular waves. The hybrid control strategy has been evaluated against the reference baseline controller embedded in FAST in different environmental scenarios. The comparison is assessed in terms of output power and structure stability, with up to 23% and 33% vibration suppression rate for tower top displacement and platform pitch, respectively, with the new control scheme. Fatigue damage equivalent load (DEL) of the blades has been also estimated with satisfactory results., This work has been partially supported by the Spanish Ministry of Science and Innovation under the project MCI/AEI/FEDER number RTI2018-094902-B-C21 and PDI2021-123543OB-C21.
Docta Complutense
Publicación Capítulo o parte de un libro (BookPart)

Control tuning by genetic algorithm of a low scale model wind turbine

  • Andrade Aimara , Giordy Alexander
  • Esteban San Román, Segundo
  • Santos Peñas, Matilde
The continuous rise of wind energy makes it necessary to design controllers that make turbines more and more efficient. However, control designs are usually developed in simulation, which does not consider the many factors that affect control in a real turbine. An intermediate step, before testing them on turbines, is to check them on prototypes. In this paper, a first design of a laboratory scale model of a wind turbine (WT) is proposed, with the aim of testing different control algorithms. The model is built with commercial hardware and “ad hoc” circuits. Two control loops have been implemented; an external loop that commands the electric charge, and an internal loop that controls the pitch of the blades. The controllers have been tuned first experimentally, obtaining the best possible behavior by trial and error. Using genetic algorithms, the most optimal values for the controller are obtained, improving the response of the system. The operating and functional modes of a real WT have been also replicated on the model using a microcontroller programmed with the Arduino IDE input-output. Results obtained using optimized conventional controllers prove the correct performance of the prototype.