Scholarlink

<p>In the current study, an attempt is made to improve the pavement’s subbase layer with Xanthan Gum (XG) biopolymer. Utilizing cement and lime results in the production of greenhouse gases, which negatively impact the environment. The experimental results indicate that the XG biopolymer can serve as an alternative to the traditional stabilizers cement and lime. Resilient modulus (<i>M</i><sub>R</sub>) is a crucial parameter for pavement stability, underscoring its significance in understanding soil behavior and pavement design. AASTHO and IRC advise using <i>M</i><sub>R</sub> in designing and analyzing multi-layered pavement systems. Biopolymer percentage, curing days, and UCS are input parameters for <i>M</i><sub>R</sub>, which are predicted using AI-ML models. Four AI-ML models are implied in the present study, and the best possible fit model among them is validated. Decision tree AI-ML model is the best-fit model among the implied models with 96.66% accuracy. The proposed optimization approach will modernize the way engineers and designers work by estimating strength parameters before testing, ultimately saving valuable time and resources. This innovative method is set to streamline processes and enhance efficiency in the field of engineering.</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

A Strategic Approach to Predict the Resilient Modulus of Biopolymer-Treated Soil Using Artificial Intelligence: Machine Learning Techniques

  • 期刊论文

  • 发表日期：

    2025年9月11日

查看全文
  • Rakesh Pydi,
  • Laxmikant Yadu,
  • Sandeep Kumar Chouksey

摘要

In the current study, an attempt is made to improve the pavement’s subbase layer with Xanthan Gum (XG) biopolymer. Utilizing cement and lime results in the production of greenhouse gases, which negatively impact the environment. The experimental results indicate that the XG biopolymer can serve as an alternative to the traditional stabilizers cement and lime. Resilient modulus (MR) is a crucial parameter for pavement stability, underscoring its significance in understanding soil behavior and pavement design. AASTHO and IRC advise using MR in designing and analyzing multi-layered pavement systems. Biopolymer percentage, curing days, and UCS are input parameters for MR, which are predicted using AI-ML models. Four AI-ML models are implied in the present study, and the best possible fit model among them is validated. Decision tree AI-ML model is the best-fit model among the implied models with 96.66% accuracy. The proposed optimization approach will modernize the way engineers and designers work by estimating strength parameters before testing, ultimately saving valuable time and resources. This innovative method is set to streamline processes and enhance efficiency in the field of engineering.