Scholarlink

<p>The article explores the impact of data analytics in strengthening safety measures within the mining sector, an industry characterized by inherent risks and operational challenges. It examines the application of advanced analytical techniques, including predictive modelling, machine learning algorithms, and real-time monitoring systems, to proactively mitigate hazards and improve workplace safety. Key applications such as accident prediction, equipment failure prediction, and environmental hazard detection are critically analysed, highlighting their effectiveness in reducing risks and minimizing operational downtime. A case study on mining equipment failure prediction demonstrates the efficacy of machine learning-based predictive maintenance, where ensemble models such as XGBoost and Random Forest achieved an accuracy of 98.55% &amp; 98.20% respectively, with superior precision and recall. These findings validate the potential of advanced machine learning techniques in identifying failures with minimal false predictions, thereby improving operational reliability and safety. By consolidating recent advancements and offering actionable insights, this paper provides a perspective on leveraging data-driven strategies for safer, more efficient, and sustainable mining operations.</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

Machine learning-based predictive models for enhancing safety and preventing failures in mining operations

  • 期刊论文

  • 发表日期：

    2025年12月4日

查看全文
  • Farooq Ahmed Siddique K,
  • Debi Prasad Tripathy,
  • Santosh Kumar Nanda

摘要

The article explores the impact of data analytics in strengthening safety measures within the mining sector, an industry characterized by inherent risks and operational challenges. It examines the application of advanced analytical techniques, including predictive modelling, machine learning algorithms, and real-time monitoring systems, to proactively mitigate hazards and improve workplace safety. Key applications such as accident prediction, equipment failure prediction, and environmental hazard detection are critically analysed, highlighting their effectiveness in reducing risks and minimizing operational downtime. A case study on mining equipment failure prediction demonstrates the efficacy of machine learning-based predictive maintenance, where ensemble models such as XGBoost and Random Forest achieved an accuracy of 98.55% & 98.20% respectively, with superior precision and recall. These findings validate the potential of advanced machine learning techniques in identifying failures with minimal false predictions, thereby improving operational reliability and safety. By consolidating recent advancements and offering actionable insights, this paper provides a perspective on leveraging data-driven strategies for safer, more efficient, and sustainable mining operations.