Scholarlink

<p>Concrete is one of the most widely used construction materials and may experience cracking and erosion over time, leading to reduced strength and structural performance. Using recycled concrete as aggregate is an effective approach to minimize construction waste. This study employs a hybrid computational approach combining Genetic Algorithm (GA) and Artificial Neural Networks (ANN) to predict the mechanical behavior of recycled aggregate concrete cylinders reinforced with Fiber-Reinforced Polymer (FRP) tubes. Laboratory data from the research of Jin and Yan, involving two types of FRP—flax and polyester—were utilized. The developed model demonstrated high accuracy in predicting compressive strength (R<sup>2</sup> = 0.94) and ultimate strain (R<sup>2</sup> = 0.91). Sensitivity analysis revealed that the elastic modulus, tensile strength, and thickness of the FRP layers have the most significant impact on the stress–strain response. These results confirm the model’s reliability and its potential application in designing sustainable and efficient reinforced concrete 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

Prediction of compressive strength of recycled concrete cylinders reinforced with fiber-reinforced polymer using a combined genetic algorithm and neural network approach

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月2日

查看全文
  • Hossein Khosravi,
  • Marzie Mohammadi Pour,
  • Mohammad Bahram

摘要

Concrete is one of the most widely used construction materials and may experience cracking and erosion over time, leading to reduced strength and structural performance. Using recycled concrete as aggregate is an effective approach to minimize construction waste. This study employs a hybrid computational approach combining Genetic Algorithm (GA) and Artificial Neural Networks (ANN) to predict the mechanical behavior of recycled aggregate concrete cylinders reinforced with Fiber-Reinforced Polymer (FRP) tubes. Laboratory data from the research of Jin and Yan, involving two types of FRP—flax and polyester—were utilized. The developed model demonstrated high accuracy in predicting compressive strength (R2 = 0.94) and ultimate strain (R2 = 0.91). Sensitivity analysis revealed that the elastic modulus, tensile strength, and thickness of the FRP layers have the most significant impact on the stress–strain response. These results confirm the model’s reliability and its potential application in designing sustainable and efficient reinforced concrete structures.