Scholarlink

This study presents a genetic algorithm (GA)-based approach to optimize anaerobic biogas production (ABP) under varying process conditions for sustainable applications in green buildings. The optimization objective was to maximize ABP volume (measured in mL) by tuning five key process variables: substrate-to-water ratio (S/W), co-substrate-to-water ratio (C/W), pH, temperature, and retention time. A response surface model was developed using Central Composite Design (CCD) and integrated with a GA in MATLAB for dynamic optimization. Dashboard visualizations enabled real-time tracking of sensitivity, convergence, and variable interactions. The optimal conditions discovered led to a 12.4% increase in ABP compared to baseline values. Sensitivity analysis revealed pH and retention time as dominant factors. The results confirm the utility of evolutionary algorithms for improving energy yield in biogas systems, offering data-driven decision-making tools for environmentally conscious architectural systems.

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 Biogas Yield via Genetic Algorithms for Green Building Use

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Niloofar Rouhani,
  • Mohammad Gheibi,
  • Klodian Dhoska,
  • Andres Annuk,
  • Reza Moezzi

摘要

This study presents a genetic algorithm (GA)-based approach to optimize anaerobic biogas production (ABP) under varying process conditions for sustainable applications in green buildings. The optimization objective was to maximize ABP volume (measured in mL) by tuning five key process variables: substrate-to-water ratio (S/W), co-substrate-to-water ratio (C/W), pH, temperature, and retention time. A response surface model was developed using Central Composite Design (CCD) and integrated with a GA in MATLAB for dynamic optimization. Dashboard visualizations enabled real-time tracking of sensitivity, convergence, and variable interactions. The optimal conditions discovered led to a 12.4% increase in ABP compared to baseline values. Sensitivity analysis revealed pH and retention time as dominant factors. The results confirm the utility of evolutionary algorithms for improving energy yield in biogas systems, offering data-driven decision-making tools for environmentally conscious architectural systems.