Scholarlink

<p>It has been demonstrated that adding steel fibers to regular concrete significantly increases the structural components’ ability to support loads. Accurate models for predicting the mechanical properties of steel fiber reinforced concrete (SFRC) are lacking, and the impact of fibers on the fundamental mechanical properties of SFRC and the associated uncertainties are not well described. This significantly lessens its applicability in actual structures. This study looks at a number of variables related to elastic modulus E<sub>cy</sub>, including the water-to-cement ratio, sand-to-cement mass ratio, coarse aggregate-to-cement mass proportion, fiber reinforcement coefficient, fiber morphology parameter, coarse aggregate size, superplasticizer-to-cement mass ratio, as well as fiber tensile yield strength. The three types of fibers used in this study are hooked, mill-cut, and crimped. This study assesses three strategies for predicting E<sub>cy</sub>, with a focus on the utilization of the Chaos game algorithm (CGA), a hybrid optimization technique, with Random Forests (RF) and Adaptive neuro-fuzzy inference system (ANFIS) techniques. According to the ANFIS (CGA), the U_(95%) index values for the assessment and learning stages were 1.4251 and 1.95, respectively. For the RF (CGA), the equivalent U_(95%) values were 2.7299 and 2.8065. It has been determined that all single models are regarded as reliable and believable after assessing rating levels, logical inference, and assessment elements. From an objective point of view, the ANFIS (CGA) model is a little better than the alternative model.</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 a Powerful Fuzzy System on the Elastic Modulus of Steel Fiber-Reinforced Concrete in Post-grouting Piles

  • 期刊论文

  • 发表日期：

    2026年4月8日

查看全文
  • Ziru Su,
  • Liang Li,
  • Zhijiang Lan,
  • Shaohuang Zhuang,
  • Song Liao,
  • Xianlin Fan,
  • Dongyun Xian

摘要

It has been demonstrated that adding steel fibers to regular concrete significantly increases the structural components’ ability to support loads. Accurate models for predicting the mechanical properties of steel fiber reinforced concrete (SFRC) are lacking, and the impact of fibers on the fundamental mechanical properties of SFRC and the associated uncertainties are not well described. This significantly lessens its applicability in actual structures. This study looks at a number of variables related to elastic modulus Ecy, including the water-to-cement ratio, sand-to-cement mass ratio, coarse aggregate-to-cement mass proportion, fiber reinforcement coefficient, fiber morphology parameter, coarse aggregate size, superplasticizer-to-cement mass ratio, as well as fiber tensile yield strength. The three types of fibers used in this study are hooked, mill-cut, and crimped. This study assesses three strategies for predicting Ecy, with a focus on the utilization of the Chaos game algorithm (CGA), a hybrid optimization technique, with Random Forests (RF) and Adaptive neuro-fuzzy inference system (ANFIS) techniques. According to the ANFIS (CGA), the U_(95%) index values for the assessment and learning stages were 1.4251 and 1.95, respectively. For the RF (CGA), the equivalent U_(95%) values were 2.7299 and 2.8065. It has been determined that all single models are regarded as reliable and believable after assessing rating levels, logical inference, and assessment elements. From an objective point of view, the ANFIS (CGA) model is a little better than the alternative model.