Scholarlink

<p>Evaluation of torsional strength poses a significant challenge in reinforced concrete due to its inherently complex nature. As a fundamental aspect of structural behavior, accurately assessing torsional strength requires physical testing of structural elements. However, such testing is limited by the scarcity and high cost of specialized equipment. To overcome this challenge, this study proposes the use of nomogram derived through a neural network-genetic algorithm model. A comprehensive dataset consisting of 173 experimentally obtained results was employed to develop the neuro-genetic algorithm–based torsional strength model. The model focused on key input parameters such as area, compressive strength, and the influence of longitudinal and transverse reinforcement. The results demonstrated that the developed nomogram exhibited strong predictive performance, closely matching the accuracy of the neuro-genetic algorithm from which it was derived. With a high correlation coefficient of 0.99 and a root mean squared error of just 5.10, the nomogram proved to be a reliable and effective tool for estimating torsional strength of reinforced concrete. The nomogram works as a novel non-destructive testing tool, with the predicted results offering valuable baseline information for the design of reinforced concrete members.</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

Development of nomogram for torsional strength of reinforced concrete using hybrid machine learning algorithm

  • 期刊论文

  • 发表日期：

    2026年2月5日

查看全文
  • Nolan Concha,
  • Cindelyn Acuyado,
  • Ayke Bernal,
  • Zordic Grey Dumag,
  • John Eazer Francisco,
  • Kenneth Carl Prado

摘要

Evaluation of torsional strength poses a significant challenge in reinforced concrete due to its inherently complex nature. As a fundamental aspect of structural behavior, accurately assessing torsional strength requires physical testing of structural elements. However, such testing is limited by the scarcity and high cost of specialized equipment. To overcome this challenge, this study proposes the use of nomogram derived through a neural network-genetic algorithm model. A comprehensive dataset consisting of 173 experimentally obtained results was employed to develop the neuro-genetic algorithm–based torsional strength model. The model focused on key input parameters such as area, compressive strength, and the influence of longitudinal and transverse reinforcement. The results demonstrated that the developed nomogram exhibited strong predictive performance, closely matching the accuracy of the neuro-genetic algorithm from which it was derived. With a high correlation coefficient of 0.99 and a root mean squared error of just 5.10, the nomogram proved to be a reliable and effective tool for estimating torsional strength of reinforced concrete. The nomogram works as a novel non-destructive testing tool, with the predicted results offering valuable baseline information for the design of reinforced concrete members.