Load mitigation of a class of 5-MW wind turbine with RBF neural network based fractional-order PID controller

A. H. Asgharnia (Corresponding Author), A. Jamali, R. Shahnazi, A. Maheri

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In variable-pitch wind turbines, pitch angle control is implemented to regulate the rotor speed and power production. However, mechanical loads of the wind turbines are affected by the pitch angle adjustment. To improve the performance and at the same time alleviate the mechanical loads, a gain-scheduling fractional-order PID (FOPID), where a trained RBF neural network chooses its parameters is proposed. The database, which the RBF neural network is trained based on, is created via optimization of a FOPID in several wind speeds with chaotic differential evolution (CDE) algorithm. The simulation results are compared to an RBF based PID controller that is designed via the same method, a conventional gain-scheduling baseline PI controller developed by NREL, an optimal RBF based PI controller, and a FOPI controller. The simulations indicate that the RBF based FOPID improves the control performance of the benchmark wind turbine in comparison to the other controllers, while the applied loads to the structure are mitigated. To validate the performance and robustness, all controllers are implemented on FAST wind turbine simulator. The superiority of the proposed FOPID controller is depicted in comparison to the other controllers.
Original languageEnglish
JournalISA Transactions
Early online date4 Jul 2019
DOIs
Publication statusE-pub ahead of print - 4 Jul 2019

Fingerprint

RBF Neural Network
wind turbines
Wind Turbine
PID Controller
Fractional Order
Wind turbines
controllers
Gain Scheduling
Neural networks
Controller
Controllers
PI Controller
Angle
Differential Evolution Algorithm
pitch (inclination)
scheduling
Wind Speed
Rotor
Baseline
Adjustment

Keywords

  • Gain-scheduling fractional-order PID
  • Wind turbine pitch control
  • Chaotic differential evolution
  • RBF neural network
  • FAST

Cite this

Load mitigation of a class of 5-MW wind turbine with RBF neural network based fractional-order PID controller. / Asgharnia, A. H. (Corresponding Author); Jamali, A.; Shahnazi, R.; Maheri, A.

In: ISA Transactions, 04.07.2019.

Research output: Contribution to journalArticle

@article{68899245c1ba4dde87d04a9432b89ec5,
title = "Load mitigation of a class of 5-MW wind turbine with RBF neural network based fractional-order PID controller",
abstract = "In variable-pitch wind turbines, pitch angle control is implemented to regulate the rotor speed and power production. However, mechanical loads of the wind turbines are affected by the pitch angle adjustment. To improve the performance and at the same time alleviate the mechanical loads, a gain-scheduling fractional-order PID (FOPID), where a trained RBF neural network chooses its parameters is proposed. The database, which the RBF neural network is trained based on, is created via optimization of a FOPID in several wind speeds with chaotic differential evolution (CDE) algorithm. The simulation results are compared to an RBF based PID controller that is designed via the same method, a conventional gain-scheduling baseline PI controller developed by NREL, an optimal RBF based PI controller, and a FOPI controller. The simulations indicate that the RBF based FOPID improves the control performance of the benchmark wind turbine in comparison to the other controllers, while the applied loads to the structure are mitigated. To validate the performance and robustness, all controllers are implemented on FAST wind turbine simulator. The superiority of the proposed FOPID controller is depicted in comparison to the other controllers.",
keywords = "Gain-scheduling fractional-order PID, Wind turbine pitch control, Chaotic differential evolution, RBF neural network, FAST",
author = "Asgharnia, {A. H.} and A. Jamali and R. Shahnazi and A. Maheri",
year = "2019",
month = "7",
day = "4",
doi = "10.1016/j.isatra.2019.07.006",
language = "English",
journal = "ISA Transactions",
issn = "0019-0578",
publisher = "Elsevier",

}

TY - JOUR

T1 - Load mitigation of a class of 5-MW wind turbine with RBF neural network based fractional-order PID controller

AU - Asgharnia, A. H.

AU - Jamali, A.

AU - Shahnazi, R.

AU - Maheri, A.

PY - 2019/7/4

Y1 - 2019/7/4

N2 - In variable-pitch wind turbines, pitch angle control is implemented to regulate the rotor speed and power production. However, mechanical loads of the wind turbines are affected by the pitch angle adjustment. To improve the performance and at the same time alleviate the mechanical loads, a gain-scheduling fractional-order PID (FOPID), where a trained RBF neural network chooses its parameters is proposed. The database, which the RBF neural network is trained based on, is created via optimization of a FOPID in several wind speeds with chaotic differential evolution (CDE) algorithm. The simulation results are compared to an RBF based PID controller that is designed via the same method, a conventional gain-scheduling baseline PI controller developed by NREL, an optimal RBF based PI controller, and a FOPI controller. The simulations indicate that the RBF based FOPID improves the control performance of the benchmark wind turbine in comparison to the other controllers, while the applied loads to the structure are mitigated. To validate the performance and robustness, all controllers are implemented on FAST wind turbine simulator. The superiority of the proposed FOPID controller is depicted in comparison to the other controllers.

AB - In variable-pitch wind turbines, pitch angle control is implemented to regulate the rotor speed and power production. However, mechanical loads of the wind turbines are affected by the pitch angle adjustment. To improve the performance and at the same time alleviate the mechanical loads, a gain-scheduling fractional-order PID (FOPID), where a trained RBF neural network chooses its parameters is proposed. The database, which the RBF neural network is trained based on, is created via optimization of a FOPID in several wind speeds with chaotic differential evolution (CDE) algorithm. The simulation results are compared to an RBF based PID controller that is designed via the same method, a conventional gain-scheduling baseline PI controller developed by NREL, an optimal RBF based PI controller, and a FOPI controller. The simulations indicate that the RBF based FOPID improves the control performance of the benchmark wind turbine in comparison to the other controllers, while the applied loads to the structure are mitigated. To validate the performance and robustness, all controllers are implemented on FAST wind turbine simulator. The superiority of the proposed FOPID controller is depicted in comparison to the other controllers.

KW - Gain-scheduling fractional-order PID

KW - Wind turbine pitch control

KW - Chaotic differential evolution

KW - RBF neural network

KW - FAST

UR - http://www.mendeley.com/research/load-mitigation-class-5mw-wind-turbine-rbf-neural-network-based-fractionalorder-pid-controller

U2 - 10.1016/j.isatra.2019.07.006

DO - 10.1016/j.isatra.2019.07.006

M3 - Article

JO - ISA Transactions

JF - ISA Transactions

SN - 0019-0578

ER -