Scholarlink

<p>Static elastic modulus (<i>E</i><sub>s</sub>) and dynamic elastic modulus (<i>E</i><sub>d</sub>) are two important parameters in rock mechanics that indicate the resistance to deformation under constant and variable loads, respectively. In this study, <i>E</i><sub>s</sub> and <i>E</i><sub>d</sub> were predicted based on physical and textural properties using ML and statistical models. Statistical analysis showed that textural properties have a greater effect than physical features on <i>E</i><sub>d</sub> and <i>E</i><sub>s</sub>. The presence of wackestone and mudstone tends to reduce the elastic properties of rocks, whereas packstone contributes to enhancing these characteristics. The ratio of <i>E</i><sub>d</sub> to <i>E</i><sub>s</sub> for the samples in the present study was found to be equal to 1.14. The relationship between these two parameters, based on the most accurate fit, is a Linear function with a correlation coefficient of 93%. Support vector regression based on radial basis kernel function (SVR-RBF), feedforward multilayer perceptron neural network (FMLPNN), and K-nearest neighbor (KNN), multivariate linear regression (MLR), and random forest (RF) were used to estimate the <i>E</i><sub>s</sub> and <i>E</i><sub>d</sub>. Based on various statistical criteria, the FMLPNN with an <i>R</i><sup>2</sup> = 0.99 and RMSE = 0.07 to estimate <i>E</i><sub>d</sub> and an <i>R</i><sup>2</sup> = 1.00 and RMSE = 0.01 for estimating <i>E</i><sub>s</sub> demonstrated greater accuracy compared to the other models.</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

Estimation of elastic modulus of carbonate rocks using statistical and soft computing approaches

  • 期刊论文

  • 发表日期：

    2025年9月15日

查看全文
  • Zhou Zhou,
  • Lei Cao,
  • Zhe Wang,
  • Na Liu,
  • K D V Prasad

摘要

Static elastic modulus (Es) and dynamic elastic modulus (Ed) are two important parameters in rock mechanics that indicate the resistance to deformation under constant and variable loads, respectively. In this study, Es and Ed were predicted based on physical and textural properties using ML and statistical models. Statistical analysis showed that textural properties have a greater effect than physical features on Ed and Es. The presence of wackestone and mudstone tends to reduce the elastic properties of rocks, whereas packstone contributes to enhancing these characteristics. The ratio of Ed to Es for the samples in the present study was found to be equal to 1.14. The relationship between these two parameters, based on the most accurate fit, is a Linear function with a correlation coefficient of 93%. Support vector regression based on radial basis kernel function (SVR-RBF), feedforward multilayer perceptron neural network (FMLPNN), and K-nearest neighbor (KNN), multivariate linear regression (MLR), and random forest (RF) were used to estimate the Es and Ed. Based on various statistical criteria, the FMLPNN with an R2 = 0.99 and RMSE = 0.07 to estimate Ed and an R2 = 1.00 and RMSE = 0.01 for estimating Es demonstrated greater accuracy compared to the other models.