基于改进DBScan算法的雷暴挖掘与研究  

Excavation and Research of Thunderstorm Based on Improved DBScan Algorithm

作　　者：高攀 田浩[2,3] 李健 陶汉涛[2,3] 王钊 姜志博 GAO Pan;TIAN Hao;LI Jian;TAO Hantao;WANG Zhao;JIANG Zhibo(NARI Group Corporation(State Grid Electric Power Research Institute), Nanjing 211106, China;Wuhan NARI Co., Ltd., State Grid Electric Power Research Institute, Wuhan 430074, China;Hubei Key Laboratory of PowerGrid Lightning Risk Prevention, Wuhan 430074, China)

机构地区：[1]南瑞集团公司(国网电力科学研究院),南京211106 [2]国网电力科学研究院武汉南瑞有限责任公司,武汉430074 [3]电网雷击风险预防湖北省重点实验室,武汉430074

出　　处：《高压电器》2019年第4期169-177,共9页High Voltage Apparatus

基　　金：国家自然科学基金项目(51777037);国家电网公司科技指南项目(524625170011)~~

摘　　要：为了从已发生的雷电现象中提取雷暴并研究雷暴活动规律。文中根据雷电定位系统采集的雷电数据,使用大数据、数据挖掘等计算机技术,开发基于Spark框架的改进DBScan算法,进行雷电聚类分析,提取雷暴,在ArcGIS软件中动态分析雷暴产生、爆发、移动、消亡全过程,最后通过计算机对雷暴进行分析统计,寻找雷暴活动规律。根据历史雷电数据逆向挖掘雷暴,掌握雷暴的活动规律,对今后雷暴预警奠定基础。In order to extract thunderstorms from existing lightning phenomena and study thunderstorm activity law, based on the lightning data collected by the lightning location system, this paper develops an improved DBScan algo rithm based on Spark framework, carries out lightning clustering analysis, extracts thunderstorms, dynamically analyzes the whole process of thunderstorms' occurrence, outbreak, movement and extinction in ArcGIS software, and finally checks them by computer. Thunderstorms are analyzed statistically to find thunderstorm activity rules. According to the historical thunderstorm data, the thunderstorm is excavated in reverse, and the thunderstorm activity law is mastered, which lay a foundation for thunderstorm early warning in the future.

关 键 词：海量雷电数据 雷暴聚类 改进DBScan算法 雷暴动态分析 雷暴活动规律 

分 类 号：TM863[电气工程—高电压与绝缘技术] P446[天文地球—大气科学及气象学]