Scholarlink

<p>The research presents Snow Ablation Optimized Multi-strategy Particle Swarm Optimization (SAO-MPSO) as an algorithm to perform accurate parameter estimation of proton exchange membrane fuel cells (PEMFCs). The four optimization methods PSO, PPSO, AGPSO, and VPPSO fail to achieve proper exploration–exploitation balance which results in poor parameter tuning outcomes. SAO-MPSO assumes a framework where snow ablation search elements combine with multi-strategy reproduction methods to accelerate both speed-to-convergence and analysis precision. SAO-MPSO demonstrates excellent accuracy and stability when tested on six commercial PEMFC models under different operating conditions. SAO-MPSO demonstrates superior performance by reaching the lowest error metrics alongside the fastest convergence speed thus becoming an optimal optimization tool for PEMFC modeling. The obtained results demonstrate the reliability of this method for fuel cell parameter optimization which can lead to its application in real-time energy systems. The upcoming research will concentrate on developing SAO-MPSO for extensive fuel cell implementations and additional energy technology domains.</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

A hybrid snow ablation optimized multi-strategy particle swarm optimizer for parameter estimation of proton exchange membrane fuel cell

  • 期刊论文

  • 发表日期：

    2025年3月17日

查看全文
  • Mohammad Aljaidi,
  • Sunilkumar P. Agrawal,
  • Anil Parmar,
  • Pradeep Jangir,
  • Arpita,
  • Bhargavi Indrajit Trivedi,
  • Gulothungan G.,
  • Reena Jangid,
  • Ali Fayez Alkoradees

摘要

The research presents Snow Ablation Optimized Multi-strategy Particle Swarm Optimization (SAO-MPSO) as an algorithm to perform accurate parameter estimation of proton exchange membrane fuel cells (PEMFCs). The four optimization methods PSO, PPSO, AGPSO, and VPPSO fail to achieve proper exploration–exploitation balance which results in poor parameter tuning outcomes. SAO-MPSO assumes a framework where snow ablation search elements combine with multi-strategy reproduction methods to accelerate both speed-to-convergence and analysis precision. SAO-MPSO demonstrates excellent accuracy and stability when tested on six commercial PEMFC models under different operating conditions. SAO-MPSO demonstrates superior performance by reaching the lowest error metrics alongside the fastest convergence speed thus becoming an optimal optimization tool for PEMFC modeling. The obtained results demonstrate the reliability of this method for fuel cell parameter optimization which can lead to its application in real-time energy systems. The upcoming research will concentrate on developing SAO-MPSO for extensive fuel cell implementations and additional energy technology domains.