摘要：矿井通风系统异常可侧面反映出矿井生产系统中存在的风险和隐患状态。论文通过将示范矿井基础信息和通风监测数据和生产状态相结合，借助数据挖掘算法，研究生产时期矿井通风系统监测数据的异常变化特性，进而构建风险监测预警模型。应用邻近算法实现对有效过滤后的通风数据的分析，提取出示范煤矿通风系统显现出的主要灾害风险点。利用粒子群算法计算风险点监测范围，并基于风险点的演化路径构建出矿井风险评估标准和风险超前预警响应模型。论文的研究可为实现矿井风险的超前预警智能化管理提供理论支持。

TOPIC：The study of risk monitoring and early warning model in coalmine based on data mining
ABSTRCT：Abnormal levels of mine ventilation system can reflect the risks and hidden dangers existing in the mine production system to some extent. By combining the basic information with the ventilation monitoring data and the production state, this paper studid the abnormal change characteristics of the mine ventilation system monitoring data in the production period, and then constructing the risk monitoring and early warning model. The adjacent algorithm was applied to realize the analysis of the effectively filtered ventilation data, and to extract the main disaster risk points shown in the coal mine ventilation system. The particle group algorithm was used to calculate the risk point monitoring range, and to construct the mine risk assessment standard and the risk early warning response model based on the evolution path of the risk point. The research of the paper can provide theoretical support for the realization of intelligent management of mine risk.
 

数据挖掘算法