Scholarlink

<p>Doubly Fed Induction Generators (DFIGs) are extensively used in Wind Energy Conversion Systems (WECSs) due to their variable speed operation; however, this feature hinders the extraction of maximum power. Traditional control approaches, particularly Direct Power Control (DPC), have some drawbacks, including power fluctuations, switching ripples, and poor dynamic performance. This paper presents an Adaptive Predictive Fuzzy Logic Neural Network Controller (APFNNC) for maximizing the power from DFIG-WECS-based DPC. This proposed hybrid technique integrates the straightforwardness of fuzzy logic with the self-learning and generalization characteristics of neural networks, enhanced by predictive adaptation to predict system dynamics. This facilitates precise maximum power point monitoring while enhancing active and reactive powers and current profiles. The effectiveness of the APFNNC is confirmed by MATLAB/Simulink simulations, which show that it has less power and torque oscillations, a more stable DC-link voltage, and a lower root mean square error (RMSE) than typical fuzzy logic and artificial neural network controllers. The results validate the APFNNC's reliability and efficiency in boosting power extraction in variable wind conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive Predictive-Fuzzy Logic Neural Network Controller for Maximizing the Extracted Power from Wind Energy Conversion System-Based Doubly Fed Induction Generator

  • 期刊论文

  • 发表日期：

    2026年1月7日

查看全文
  • Mohamed I. Mosaad

摘要

Doubly Fed Induction Generators (DFIGs) are extensively used in Wind Energy Conversion Systems (WECSs) due to their variable speed operation; however, this feature hinders the extraction of maximum power. Traditional control approaches, particularly Direct Power Control (DPC), have some drawbacks, including power fluctuations, switching ripples, and poor dynamic performance. This paper presents an Adaptive Predictive Fuzzy Logic Neural Network Controller (APFNNC) for maximizing the power from DFIG-WECS-based DPC. This proposed hybrid technique integrates the straightforwardness of fuzzy logic with the self-learning and generalization characteristics of neural networks, enhanced by predictive adaptation to predict system dynamics. This facilitates precise maximum power point monitoring while enhancing active and reactive powers and current profiles. The effectiveness of the APFNNC is confirmed by MATLAB/Simulink simulations, which show that it has less power and torque oscillations, a more stable DC-link voltage, and a lower root mean square error (RMSE) than typical fuzzy logic and artificial neural network controllers. The results validate the APFNNC's reliability and efficiency in boosting power extraction in variable wind conditions.