Scholarlink

<p>In the earlier stages of mine planning, geo-engineers and planners need a reliable estimation of ripper production. For weak and fractured rocks, definitive geotechnical information has the potential to yield an estimate of the mine site rippability. These parameters usually have some hidden pattern relating them with ripper production for machine being employed. Today, in the era of advanced computing and artificial intelligence, decoding these hidden patterns through machine learning techniques have become a viable option. Therefore, in the present research the rippability estimation was accomplished through several ensemble machine learning techniques based on the five laboratory tested data. Ensemble models like Extra Tree, Gradient Boosting, Histogram Gradient Boosting, AdaBoost, Bagging, and Voting have been developed in the present work. The five geotechnical attributes viz., uniaxial compressive strength, Brazilian tensile strength, slake durability index, point load index, &amp; <i>P</i>-wave velocity have been used as feature variables. The influence on rock mass weathering grade on ripper production has also been investigated in the present research. Additionally, a linear regression model was developed to compare the accuracy of the advanced artificial intelligence models with it. The statistical means to compare the prediction accuracy of the presently developed algorithms are the <i>R</i><sup>2</sup> and mean absolute error (MAE). The Extra Tree regressor beats all other models and achieved a highest <i>R</i><sup>2</sup> and least MAE value among all other algorithms. Comparatively, linear model had displayed statistically impoverished performance in the present research&#xa0;work.</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

Ensemble Algorithms for Prediction of Ripping Production in Sedimentary Rocks

  • 期刊论文

  • 发表日期：

    2025年5月26日

查看全文
  • Edy Tonnizam Mohamad,
  • Ramesh Murlidhar Bhatawdekar,
  • Vishnu Himanshu Ratnam Pandey,
  • Ashuthosh Kainthola

摘要

In the earlier stages of mine planning, geo-engineers and planners need a reliable estimation of ripper production. For weak and fractured rocks, definitive geotechnical information has the potential to yield an estimate of the mine site rippability. These parameters usually have some hidden pattern relating them with ripper production for machine being employed. Today, in the era of advanced computing and artificial intelligence, decoding these hidden patterns through machine learning techniques have become a viable option. Therefore, in the present research the rippability estimation was accomplished through several ensemble machine learning techniques based on the five laboratory tested data. Ensemble models like Extra Tree, Gradient Boosting, Histogram Gradient Boosting, AdaBoost, Bagging, and Voting have been developed in the present work. The five geotechnical attributes viz., uniaxial compressive strength, Brazilian tensile strength, slake durability index, point load index, & P-wave velocity have been used as feature variables. The influence on rock mass weathering grade on ripper production has also been investigated in the present research. Additionally, a linear regression model was developed to compare the accuracy of the advanced artificial intelligence models with it. The statistical means to compare the prediction accuracy of the presently developed algorithms are the R2 and mean absolute error (MAE). The Extra Tree regressor beats all other models and achieved a highest R2 and least MAE value among all other algorithms. Comparatively, linear model had displayed statistically impoverished performance in the present research work.