Scholarlink

<p>This study proposes an efficient and reliable predictive model for estimating the punching shear capacity of steel fiber-reinforced concrete (SFRC) slabs, developed by integrating artificial intelligence modeling, particularly multigene genetic programming (MGGP), with the mechanics of shear transfer. A dataset from existing literature was compiled and utilized to train and validated the model. The model’s performance was evaluated using different statistical metrics and compared with five existing models. Sensitivity analyses were performed to identify the influence and importance of the model parameters on predictions. To further validate the proposed model, eight SFRC slabs with different fiber volumes, flexural reinforcement ratios, concrete compressive strengths, and shear span-to-depth ratios were tested. The results indicated that employing mechanics with advanced modeling techniques effectively captured the complex interactions governing the punching shear capacity of SFRC slabs. The MGGP model demonstrated superior prediction accuracy compared to existing models, both when evaluated against the collected dataset and when validated with experimental results from the tested slabs, with the latter showing predictions within ± 10% of the measured values. Overall, the proposed model offers an efficient, simplified, and design-oriented tool for structural engineers.</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

Punching shear capacity of steel fiber-reinforced concrete flat slabs: prediction and experimental validation

  • 期刊论文

  • 发表日期：

    2025年6月24日

查看全文
  • Mohamed Eltahawy,
  • Mohamed K. Ismail,
  • Hossam A. Hodhod,
  • Wael El-Dakhakhni,
  • Hatem H. A. Ibrahim

摘要

This study proposes an efficient and reliable predictive model for estimating the punching shear capacity of steel fiber-reinforced concrete (SFRC) slabs, developed by integrating artificial intelligence modeling, particularly multigene genetic programming (MGGP), with the mechanics of shear transfer. A dataset from existing literature was compiled and utilized to train and validated the model. The model’s performance was evaluated using different statistical metrics and compared with five existing models. Sensitivity analyses were performed to identify the influence and importance of the model parameters on predictions. To further validate the proposed model, eight SFRC slabs with different fiber volumes, flexural reinforcement ratios, concrete compressive strengths, and shear span-to-depth ratios were tested. The results indicated that employing mechanics with advanced modeling techniques effectively captured the complex interactions governing the punching shear capacity of SFRC slabs. The MGGP model demonstrated superior prediction accuracy compared to existing models, both when evaluated against the collected dataset and when validated with experimental results from the tested slabs, with the latter showing predictions within ± 10% of the measured values. Overall, the proposed model offers an efficient, simplified, and design-oriented tool for structural engineers.