Scholarlink

<p>Optimization of wind energy utilization is one of the prime concerns in renewable energy projects. This paper deals with DFIG systems’ stability, an integral part of wind turbine systems. A new approach is presented, drawing on a resistor-type FCL to improve transient stability. In the recommended algorithm, the resistance of the Fault Current Limiter is tuned such that voltage magnitudes remain closer to the reference value and reduce the likelihood of system instability in case of faults. Simulations in Matlab/Simulink are performed considering symmetric and asymmetric fault scenarios. Simulation results demonstrate that FCL enhances transient stability under various cases. The study further extends to deep learning techniques for better adaptability and performance of the FCL. The deep learning model analyzes the real-time system behavior and faults; hence, the FCL adapts its parameters for better stability. Deep learning techniques greatly enhance transient stability in DFIG-centered wind energy systems. This exploration underlines the potential of integrating DL with FCL technology and points to several avenues for future exploration toward optimizing renewable energy infrastructure.</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

Enhancing Performance of Doubly Fed Induction Generator (DFIG) Wind Turbines by Incorporating Deep Learning into Fault Current Limiters (FCL)

  • 期刊论文

  • 发表日期：

    2025年7月23日

查看全文
  • Yi Zhang

摘要

Optimization of wind energy utilization is one of the prime concerns in renewable energy projects. This paper deals with DFIG systems’ stability, an integral part of wind turbine systems. A new approach is presented, drawing on a resistor-type FCL to improve transient stability. In the recommended algorithm, the resistance of the Fault Current Limiter is tuned such that voltage magnitudes remain closer to the reference value and reduce the likelihood of system instability in case of faults. Simulations in Matlab/Simulink are performed considering symmetric and asymmetric fault scenarios. Simulation results demonstrate that FCL enhances transient stability under various cases. The study further extends to deep learning techniques for better adaptability and performance of the FCL. The deep learning model analyzes the real-time system behavior and faults; hence, the FCL adapts its parameters for better stability. Deep learning techniques greatly enhance transient stability in DFIG-centered wind energy systems. This exploration underlines the potential of integrating DL with FCL technology and points to several avenues for future exploration toward optimizing renewable energy infrastructure.