Abstract: Based on database of collected gas monitoring information of coal mine monitoring system in coal mine production process,the paper put forward a scheme of using clustering analysis method based on DBSCAN algorithm to mining characteristics of gas accident information.It pointed out shortage of DBSCAN algorithm in practical application,proposed an improved scheme of DBSCAN algorithm based on data partition,and introduced the concrete improving method.The result of applying the clustering analysis method based on the improved DBSCAN algorithm to make clustering analysis and extract of information feature of gas monitoring data of coal mine showed that the method is effective.At last,the paper pointed out the farther research direction of the method.