Scholarlink

<p>Extensive research on optimizing singly and doubly reinforced concrete beams has not considerably addressed the selection of the reinforcement type when the cross-sectional dimension is constrained by factors such as story height. This study developed a genetic algorithm model to optimize the design of either singly or doubly reinforced concrete beams under restricted cross-sectional depths, thereby ensuring compliance with design standards. We constructed a dataset comprising 168 test cases, each characterized by the beam length, dead load, live load, and cross-sectional depth limitation. For validation, the actual optimal values for each case were calculated using a brute force algorithm. To enhance model stability, the best out of three optimization processes performed per data point was selected. The findings highlighted an R<sup>2</sup> value of 0.9996, thereby confirming the effectiveness of the developed model in addressing the optimization problem. This study highlights the significance of selecting an appropriate design approach based on specific conditions and recommends that future research should investigate more robust models for more complex structures.</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

Selective Cost Optimization of Singly/Doubly Reinforced Beam Design with Limited Cross-section

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月24日

查看全文
  • Dongwoo Kim,
  • Sangik Lee,
  • Jonghyuk Lee,
  • Byunghun Seo,
  • Dongsu Kim,
  • Yejin Seo,
  • Yerim Jo,
  • Won Choi

摘要

Extensive research on optimizing singly and doubly reinforced concrete beams has not considerably addressed the selection of the reinforcement type when the cross-sectional dimension is constrained by factors such as story height. This study developed a genetic algorithm model to optimize the design of either singly or doubly reinforced concrete beams under restricted cross-sectional depths, thereby ensuring compliance with design standards. We constructed a dataset comprising 168 test cases, each characterized by the beam length, dead load, live load, and cross-sectional depth limitation. For validation, the actual optimal values for each case were calculated using a brute force algorithm. To enhance model stability, the best out of three optimization processes performed per data point was selected. The findings highlighted an R2 value of 0.9996, thereby confirming the effectiveness of the developed model in addressing the optimization problem. This study highlights the significance of selecting an appropriate design approach based on specific conditions and recommends that future research should investigate more robust models for more complex structures.