Scholarlink

<p>Optimizing wind energy harvesting performance remains a significant challenge. Machine learning (ML) offers a promising approach for addressing this challenge. This study proposes an ML-based approach using the radial basis function neural network (RBFNN) and differential evolution (DE) to predict and optimize the structural parameters (the diameter of the spherical bluff body <i>D</i>, the total spring stiffness <i>k</i>, and the length of the piezoelectric cantilever beam <i>L</i>) of the wind energy harvester (WEH). The RBFNN model is trained with theoretical data and validated with wind tunnel experimental results, achieving the coefficient-of-determination scores <i>R</i><sup>2</sup> of 97.8% and 90.3% for predicting the average output power <i>P</i><sub>avg</sub> and aero-electro-mechanical efficiency <i>η</i><sub>aem</sub>, respectively. The DE algorithm is used to identify the optimal parameter combinations for wind speeds <i>U</i> ranging from 2.5 m/s to 6.5 m/s. The maximum <i>P</i><sub>avg</sub> is achieved when <i>D</i> = 57.5 mm, <i>k</i> = 28.8 N/m, <i>L</i> = 112.1 mm, and <i>U</i> = 4.6 m/s, while the maximum <i>η</i><sub>aem</sub> is achieved when <i>D</i> = 52.7 mm, <i>k</i> = 29.2 N/m, <i>L</i> = 89.2 mm, and <i>U</i> = 4.7 m/s. Compared with that of the non-optimized structure, the WEH performance is improved by 28.6% in <i>P</i><sub>avg</sub> and 19.1% in <i>η</i><sub>aem</sub>.</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

Optimizing wind energy harvester with machine learning

  • 期刊论文

  • 发表日期：

    2025年7月29日

查看全文
  • Shun Weng,
  • Liying Wu,
  • Zuoqiang Li,
  • Lanbin Zhang,
  • Huliang Dai

摘要

Optimizing wind energy harvesting performance remains a significant challenge. Machine learning (ML) offers a promising approach for addressing this challenge. This study proposes an ML-based approach using the radial basis function neural network (RBFNN) and differential evolution (DE) to predict and optimize the structural parameters (the diameter of the spherical bluff body D, the total spring stiffness k, and the length of the piezoelectric cantilever beam L) of the wind energy harvester (WEH). The RBFNN model is trained with theoretical data and validated with wind tunnel experimental results, achieving the coefficient-of-determination scores R2 of 97.8% and 90.3% for predicting the average output power Pavg and aero-electro-mechanical efficiency ηaem, respectively. The DE algorithm is used to identify the optimal parameter combinations for wind speeds U ranging from 2.5 m/s to 6.5 m/s. The maximum Pavg is achieved when D = 57.5 mm, k = 28.8 N/m, L = 112.1 mm, and U = 4.6 m/s, while the maximum ηaem is achieved when D = 52.7 mm, k = 29.2 N/m, L = 89.2 mm, and U = 4.7 m/s. Compared with that of the non-optimized structure, the WEH performance is improved by 28.6% in Pavg and 19.1% in ηaem.