Scholarlink

<p>Proton Exchange Membrane Fuel Cells (PEMFCs) are pivotal in sustainable energy systems due to their high efficiency and low environmental impact. However, the nonlinear and complex nature of PEMFC models complicates parameter estimation, hindering optimization and real-world performance. The research applies Artemisinin Optimization (AO), a metaheuristic algorithm inspired by the three-step treatment process of malaria parasites through artemisinin-based therapy, to address the challenges of PEMFC parameter estimation. The AO algorithm provides solutions to optimizing current methods through three distinctive phases: it conducts extensive global research with elimination elements followed by local exploitation with clearance steps while adding consolidation phases to stop optimizers from getting stuck at suboptimal solutions. The AO algorithm underwent extensive testing on six PEMFC stacks including BCS 500W, Nedstack 600W PS6, SR-12W, Horizon H-12, Ballard Mark V, and STD 250W. AO proved its superiority over nine state-of-the-art optimization algorithms including DE, JAYA, GSA, SCA, ACOR, HHO, MFO, WOA, and PSO through performance-based comparison. The algorithm produced the smallest mean sum of squared error value of 0.19036 while maintaining a standard deviation at 6.21E-06 to demonstrate its outstanding reliability. AO achieved the most efficient convergence rate and solved problems within 0.1385&#xa0;s during the first 50 iterations as well as resulting in faster performance than PSO (6.12&#xa0;s) and ACOR (4.88&#xa0;s). Test findings demonstrate AO powerful speed to convergence together with reliable operational outcomes and high computer processing speed throughout multiple conditions. AO delivers a balanced optimization strategy between global and local solutions and functions as a precise scalable tool to improve PEMFC design and control systems and their performance. The research contributes to PEMFC optimization methods by demonstrating the effectiveness of AO, a bio-inspired algorithm, in enhancing sustainable energy technologies. Future work will focus on adapting AO for dynamic PEMFC operation, system scale-up, and computational load reduction to improve energy system reliability and efficiency.</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

Artemisinin optimization: a new paradigm in computational efficiency and precision for PEMFC parameter estimation

  • 期刊论文

  • 发表日期：

    2025年4月14日

查看全文
  • Mohammad Aljaidi,
  • Pradeep Jangir,
  • Arpita,
  • Sunilkumar P. Agrawal,
  • Sundaram B. Pandya,
  • Anil Parmar,
  • G. Gulothungan,
  • Ali Fayez Alkoradees,
  • Reena Jangid

摘要

Proton Exchange Membrane Fuel Cells (PEMFCs) are pivotal in sustainable energy systems due to their high efficiency and low environmental impact. However, the nonlinear and complex nature of PEMFC models complicates parameter estimation, hindering optimization and real-world performance. The research applies Artemisinin Optimization (AO), a metaheuristic algorithm inspired by the three-step treatment process of malaria parasites through artemisinin-based therapy, to address the challenges of PEMFC parameter estimation. The AO algorithm provides solutions to optimizing current methods through three distinctive phases: it conducts extensive global research with elimination elements followed by local exploitation with clearance steps while adding consolidation phases to stop optimizers from getting stuck at suboptimal solutions. The AO algorithm underwent extensive testing on six PEMFC stacks including BCS 500W, Nedstack 600W PS6, SR-12W, Horizon H-12, Ballard Mark V, and STD 250W. AO proved its superiority over nine state-of-the-art optimization algorithms including DE, JAYA, GSA, SCA, ACOR, HHO, MFO, WOA, and PSO through performance-based comparison. The algorithm produced the smallest mean sum of squared error value of 0.19036 while maintaining a standard deviation at 6.21E-06 to demonstrate its outstanding reliability. AO achieved the most efficient convergence rate and solved problems within 0.1385 s during the first 50 iterations as well as resulting in faster performance than PSO (6.12 s) and ACOR (4.88 s). Test findings demonstrate AO powerful speed to convergence together with reliable operational outcomes and high computer processing speed throughout multiple conditions. AO delivers a balanced optimization strategy between global and local solutions and functions as a precise scalable tool to improve PEMFC design and control systems and their performance. The research contributes to PEMFC optimization methods by demonstrating the effectiveness of AO, a bio-inspired algorithm, in enhancing sustainable energy technologies. Future work will focus on adapting AO for dynamic PEMFC operation, system scale-up, and computational load reduction to improve energy system reliability and efficiency.