CCTEG Coal Mining Research Institute
Shaanxi Yidong Mining Company

分析了采煤工作面的隐患类型和属性,应用遗传算法建立关联规则挖掘模型,并通过文本挖掘与主题挖掘算法挖掘隐患之间的内在关系和隐患之间的关联规则,构建关联规则库。以山东某矿业公司的安全隐患检查记录为数据源,对模型进行验证,并对改进的遗传算法、遗传算法和Apriori算法进行性能对比,表明改进的遗传算法能够有效地挖掘隐患数据的关联规则,有助于加深安全管理人员对隐患数据间蕴含的内在规律的理解,为煤矿安全隐患排查治理提供依据,指导采煤生产的安全管理实践。

This study delved into the classification and attributes of potential hazards within coal mining opera-tions, utilizing a genetic algorithm to develop an association rule mining model. By integrating text mining and topic mining algorithms, it uncovered the intrinsic relationships and association rules among identified hazards, leading to the creation of an association rule database. Utilizing safety hazard inspection records from a mining company in Shandong Province as a data source, the model underwent rigorous validation. Furthermore, a com-parative analysis of the performance between the enhanced genetic algorithm and both the original genetic and Apriori algorithms was conducted. The findings demonstrate that the refined genetic algorithm is markedly effi-cient in uncovering the association rules within hidden danger data, thereby significantly enriching safety manag-ers' understanding of the underlying patterns among these data points. This enhanced insight serves as a solid foundation for the detection and remediation of safety hazards in coal mines, ultimately contributing to the ad-vancement of safety management practices in coal mining operations.

国家自然科学基金重点资助项目(51834006)

宁桂峰,高龙,刘利平.基于遗传算法的采煤工作面隐患数据关联规则挖掘[J].采矿与岩层控制工程学报,2024,6(2):023023.

NING Guifeng, GAO Long, LIU Liping. Mining hidden danger data association rules of coal mining face based on genetic algo-rithm[J]. Journal of Mining and Strata Control Engineering, 2024, 6(2): 023023.