Scholarlink

<p>Natural and man-made rock collapses are complex phenomena and cause serious dangers in many countries around the world. As a result, millions of dollars’ worth of public and private property are damaged. It is then crucial to investigate the stability of the slopes to prevent these rockfall disasters. This study presents a new approach to evaluate the probability of rock block falls on slopes, focusing on the management of geological structures that influence the stability and safety of mining operations. Because the need to support slopes is currently expensive, and in practice, their assessment is often subjective, because in some cases, the simulated failure mechanisms are not met in the field due to the existence of additional factors that are not introduced in the simulation, which motivates the search for an accurate and efficient tool that includes more variables and offers greater safety. For this reason, we propose to evaluate the stability of slopes with the help of conventional machine learning (ML) models and innovative quantum machine learning (QML) algorithms in order to ensure their structural stability. Our objective is to evaluate the various existing ML metrics with test data taken from a mine for different types of quantum embedding and to discuss their reliability. The model finds acceptable successes in the total calculation of true positives (TP) and true negatives (TN), which indicates the degree of accuracy in the positive and negative predictions made by our proposal. In this way, it is contrasted that the incorporation of QML algorithms into the application represents an innovation in the evaluation of the stability of rocky slopes, allowing to obtain a good reliability in the evaluation of the stability of the slopes.</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

Rock block fall prediction prototype by structural control applied to slopes using Quantum Machine Learning (QML)

  • 期刊论文

  • 发表日期：

    2025年1月23日

查看全文
  • Alfredo Cisneros Eufracio,
  • Roberth Saenz Perez Alvarado,
  • Jimmy Aurelio Rosales Huamani,
  • Uwe Rojas Villanueva,
  • Jose Luis Castillo Sequera,
  • Jose Manuel Gomez Pulido

摘要

Natural and man-made rock collapses are complex phenomena and cause serious dangers in many countries around the world. As a result, millions of dollars’ worth of public and private property are damaged. It is then crucial to investigate the stability of the slopes to prevent these rockfall disasters. This study presents a new approach to evaluate the probability of rock block falls on slopes, focusing on the management of geological structures that influence the stability and safety of mining operations. Because the need to support slopes is currently expensive, and in practice, their assessment is often subjective, because in some cases, the simulated failure mechanisms are not met in the field due to the existence of additional factors that are not introduced in the simulation, which motivates the search for an accurate and efficient tool that includes more variables and offers greater safety. For this reason, we propose to evaluate the stability of slopes with the help of conventional machine learning (ML) models and innovative quantum machine learning (QML) algorithms in order to ensure their structural stability. Our objective is to evaluate the various existing ML metrics with test data taken from a mine for different types of quantum embedding and to discuss their reliability. The model finds acceptable successes in the total calculation of true positives (TP) and true negatives (TN), which indicates the degree of accuracy in the positive and negative predictions made by our proposal. In this way, it is contrasted that the incorporation of QML algorithms into the application represents an innovation in the evaluation of the stability of rocky slopes, allowing to obtain a good reliability in the evaluation of the stability of the slopes.