Scholarlink

<p>Parabolic Trough Collectors (PTCs) are a well-established technology for solar energy conversion; however, the thermal losses associated with systems limit their efficiency. Integrating Heat Pipe technology with PTCs can increase the overall efficiency by improving heat transfer and minimizing the thermal resistance. This review critically identifies recent advancements in PTC–HP hybrid systems, highlighting design improvements, working fluid selection and process parameters. This review also focuses on the emerging role of machine learning (ML) algorithms such as random forests (RFs) and artificial neural networks (ANNs). Convolutional neural networks (CNNs), support vector machines (SVMs), gradient boosting regressors (GBRs) and physics-informed neural networks (PINNs) for optimization and performance prediction. This review also highlights recent findings on ML-guided heat pipe designs with improved thermal efficiency and stability for applications such as desalination plants, electricity generation and solar heating. The strategic coupling of Heat pipe technology and ML-based optimization can provide a systemic change direction for advancing solar thermal technologies to enhance the sustainable energy system. Further exploration should focus on optimizing the heat pipe integrated design with a PTC to improve system performance under dynamic solar 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

Solar parabolic trough collectors with heat pipe technology: a review of efficiency enhancement and machine learning-based optimization

  • 期刊论文

  • 发表日期：

    2025年11月27日

查看全文
  • Thilagapathy Gomupandian,
  • Ramkumar Pandian,
  • Chithirakudi Muruganandam Vivek,
  • Azim Doğuş Tuncer

摘要

Parabolic Trough Collectors (PTCs) are a well-established technology for solar energy conversion; however, the thermal losses associated with systems limit their efficiency. Integrating Heat Pipe technology with PTCs can increase the overall efficiency by improving heat transfer and minimizing the thermal resistance. This review critically identifies recent advancements in PTC–HP hybrid systems, highlighting design improvements, working fluid selection and process parameters. This review also focuses on the emerging role of machine learning (ML) algorithms such as random forests (RFs) and artificial neural networks (ANNs). Convolutional neural networks (CNNs), support vector machines (SVMs), gradient boosting regressors (GBRs) and physics-informed neural networks (PINNs) for optimization and performance prediction. This review also highlights recent findings on ML-guided heat pipe designs with improved thermal efficiency and stability for applications such as desalination plants, electricity generation and solar heating. The strategic coupling of Heat pipe technology and ML-based optimization can provide a systemic change direction for advancing solar thermal technologies to enhance the sustainable energy system. Further exploration should focus on optimizing the heat pipe integrated design with a PTC to improve system performance under dynamic solar conditions.