Scholarlink

<p>This study addresses the multi-objective trade-offs among energy consumption, thermal comfort, and construction cost in rural buildings by proposing a performance optimization framework that integrates Building Energy Simulation (BES), Artificial Neural Networks (ANN), and Multi-Criteria Decision-Making (MCDM). The method combines DesignBuilder modeling with JePlus batch simulations, incorporates the Morris method for key parameter sensitivity analysis, and utilizes MATLAB to construct an ANN-based prediction model. The TOPSIS approach is then used to select the optimal design solution. This framework significantly improves prediction accuracy and optimization efficiency under high-dimensional design spaces, overcoming the limitations of conventional platforms in convergence speed and computational complexity. A case study of a typical rural house in Chuzhou, Anhui Province, demonstrates that the optimized model reduces total energy consumption by 61.64% and discomfort hours by 32.04%, with an additional cost of ¥73,519.6, achieving a well-balanced improvement in overall performance. The study contributes a novel BES–ANN–MCDM framework, offering a replicable pathway and theoretical foundation for performance-driven, energy-efficient rural building design.</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 rural building design with an intelligent framework integrating BES ANN and MCDM

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月27日

查看全文
  • Zhongcheng Duan,
  • Renyong Zhang,
  • Yidi Zhao,
  • Chao Xie,
  • Quanming Ma

摘要

This study addresses the multi-objective trade-offs among energy consumption, thermal comfort, and construction cost in rural buildings by proposing a performance optimization framework that integrates Building Energy Simulation (BES), Artificial Neural Networks (ANN), and Multi-Criteria Decision-Making (MCDM). The method combines DesignBuilder modeling with JePlus batch simulations, incorporates the Morris method for key parameter sensitivity analysis, and utilizes MATLAB to construct an ANN-based prediction model. The TOPSIS approach is then used to select the optimal design solution. This framework significantly improves prediction accuracy and optimization efficiency under high-dimensional design spaces, overcoming the limitations of conventional platforms in convergence speed and computational complexity. A case study of a typical rural house in Chuzhou, Anhui Province, demonstrates that the optimized model reduces total energy consumption by 61.64% and discomfort hours by 32.04%, with an additional cost of ¥73,519.6, achieving a well-balanced improvement in overall performance. The study contributes a novel BES–ANN–MCDM framework, offering a replicable pathway and theoretical foundation for performance-driven, energy-efficient rural building design.