Scholarlink

<p>Natural disasters can have a high impact on property and life, and in most scenarios, such an impact can hardly be averted. In mining operations, high incidences of seismically-related events, apart from fires and explosion-related events, compound miners’ multi-faceted peril. Due to the complex processes involved in seismic activity, predicting with accuracy is not easy, even with modern tools for observation. To counteract financial loss and maximize miner security, an Extra Gradient Boosting Classification (XGBC) model is adopted to classify dangerous and safe areas in underground mining environments. An attributed analysis technique determined each contributing variable in diagnosing a case. Despite an initial run of the XGBC model producing less than satisfactory output, improvement became necessary. In an endeavor to maximize predictive performance, three improvement techniques, namely, Fox-inspired Optimization Algorithm (FOA), Coot Optimization Algorithm (COA), and Adaptive Opposition Slime Mould Algorithm (AOSM) have been adopted. Output revealed that XGFO, incorporating FOA, showed a supreme performance with a high 97.5% accuracy level. Due to its high accuracy and usability, the XGFO model is recommended for real-life use. With its optimized model, a high level of improvement in terms of security and financial loss in mining operations can be achieved, and a high demand for a reliable prediction of danger can be met.</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

Enhancing hazard prediction in coal mining with an optimized extra gradient boosting classification model for seismic bump processes

  • 期刊论文

  • 发表日期：

    2026年3月30日

查看全文
  • Fei Li

摘要

Natural disasters can have a high impact on property and life, and in most scenarios, such an impact can hardly be averted. In mining operations, high incidences of seismically-related events, apart from fires and explosion-related events, compound miners’ multi-faceted peril. Due to the complex processes involved in seismic activity, predicting with accuracy is not easy, even with modern tools for observation. To counteract financial loss and maximize miner security, an Extra Gradient Boosting Classification (XGBC) model is adopted to classify dangerous and safe areas in underground mining environments. An attributed analysis technique determined each contributing variable in diagnosing a case. Despite an initial run of the XGBC model producing less than satisfactory output, improvement became necessary. In an endeavor to maximize predictive performance, three improvement techniques, namely, Fox-inspired Optimization Algorithm (FOA), Coot Optimization Algorithm (COA), and Adaptive Opposition Slime Mould Algorithm (AOSM) have been adopted. Output revealed that XGFO, incorporating FOA, showed a supreme performance with a high 97.5% accuracy level. Due to its high accuracy and usability, the XGFO model is recommended for real-life use. With its optimized model, a high level of improvement in terms of security and financial loss in mining operations can be achieved, and a high demand for a reliable prediction of danger can be met.