Scholarlink

<p>Roof accidents are catastrophic consequences of uncontrolled roof weighting. To address the strong subjectivity and considerable delay associated with the manual analysis of hydraulic-support resistance data, this study first applies data gridding to the monitored resistance data, establishes a roof-weighting criterion for the working face, and develops a two-parameter clustering algorithm. Using the maximum inter-point distance and the minimum cluster size as its two parameters, the algorithm automatically identifies roof-weighting regions and noise points without requiring the number of clusters to be specified in advance. DBSCAN is also introduced as a comparative method to analyze roof-weighting regions and calculate periodic weighting intervals. Finally, a roof-weighting parameter extraction system is developed using the Flask framework and validated through an engineering case study of the 23,203 working face at Zhuanlongwan Coal Mine. The results show that the relative deviations of the periodic weighting intervals obtained using the two-parameter clustering algorithm and DBSCAN are 8.81% and 9.66%, respectively. The developed system enables the automated extraction of roof-weighting parameters and improves the objectivity and efficiency of mine pressure analysis.</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

Research on a roof weighting parameter mining system using support resistance manifestation information

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月2日

查看全文
  • Yuqing Wang,
  • Jianguo Du,
  • Yongkui Shi,
  • Jian Hao,
  • Daochun Yu,
  • Mengke Li

摘要

Roof accidents are catastrophic consequences of uncontrolled roof weighting. To address the strong subjectivity and considerable delay associated with the manual analysis of hydraulic-support resistance data, this study first applies data gridding to the monitored resistance data, establishes a roof-weighting criterion for the working face, and develops a two-parameter clustering algorithm. Using the maximum inter-point distance and the minimum cluster size as its two parameters, the algorithm automatically identifies roof-weighting regions and noise points without requiring the number of clusters to be specified in advance. DBSCAN is also introduced as a comparative method to analyze roof-weighting regions and calculate periodic weighting intervals. Finally, a roof-weighting parameter extraction system is developed using the Flask framework and validated through an engineering case study of the 23,203 working face at Zhuanlongwan Coal Mine. The results show that the relative deviations of the periodic weighting intervals obtained using the two-parameter clustering algorithm and DBSCAN are 8.81% and 9.66%, respectively. The developed system enables the automated extraction of roof-weighting parameters and improves the objectivity and efficiency of mine pressure analysis.