用Apriori关联规则挖掘算法发现湖北电网雷击灾害的时空分布规律
收稿日期: 2015-10-29
修回日期: 2016-03-04
网络出版日期: 2017-01-30
Spatiotemporal Distribution of Lightning Disasters of Power Lines in Hubei Province Using Data Mining Based on Apriori Association Rules
Received date: 2015-10-29
Revised date: 2016-03-04
Online published: 2017-01-30
根据湖北电网多年雷击故障数据与雷击监测数据，探究雷电活动的日分布、月分布、高程分布、二维空间分布以及时空尺度结合的分布特征，发现湖北地区雷电活动频繁的月份主要为每年七八月间，在一天之中主要集中在15：00~18：00时段；地域上主要高发于湖北黄石、咸宁东部、武汉中部、宜昌中东部、襄樊南部及北部少数地区.用Apriori关联规则对多源融合雷击数据进行挖掘得到的结果表明，输电线周围天气满足以下条件时易发生雷击故障，需加强防范：日平均相对湿度大于80%，日平均气压高于1×105 Pa，日平均水汽压在3×103~4×103 Pa之间.利用大数据关联规则对输电线周围雷击进行数据挖掘和分析可对输电线路运营规划提供指导，为电网雷击灾害防范提供决策辅助.
黄俊杰, 谭波, 陈孝明, 陈江平, 阮羚, 冯莞舒, 熊宇 . 用Apriori关联规则挖掘算法发现湖北电网雷击灾害的时空分布规律[J]. 应用科学学报, 2017 , 35(1) : 31 -41 . DOI: 10.3969/j.issn.0255-8297.2017.01.004
By using the data of lightning failure and monitoring of the past years provided by Hubei Grid, this paper studies the characteristics of daily and monthly distributions of lightning activity, as well as the elevation distribution and spatiotemporal distribution.The results show that lightning in Hubei Province mainly occurs in July and August, and between 15:00 and 18:00 during the day.The active regions include the east parts of Huangshi and Xianning, central Wuhan, central and eastern Yichang, and southern and part of northern Xiangfan.The multi-source lightning data are fused with an algorithm based on Apriori association rules.The research shows that lightning shield of the power lines may fail when daily average relative humidity is higher than 80%, daily average air pressure is higher than 1×105Pa, or daily average water vapor pressure is between 3×103 Pa and 4×103 Pa.In these cases, therefore, measures should be taken to strengthen lightning prevention.Analyzing big data of lightning around power lines using the association rules can provide guidance to decision makers of power lines for disaster prevention.
[1] 何金良,张薛巍,董林,曾嵘,刘泽洪. 输电线路雷击过程分析的雷电通道分形模型[J]. 中国科学,2009, 39(11):1818-1823. He J L, Zhang X W, Dong L, Zeng R, Liu Z H. Fractal model of lightning channel for transmission line lightning process analysis[J]. Science in China, 2009, 39(11):1818-1823. (in Chinese)
[2] 陈家宏,王海涛,冯万兴,童雪芳,李晓岚. 1000 kV线路走廊的雷电参数及易闪线段分析[J]. 高电压技术,2006, 32(12):45-48. Chen J H, Wang H T, Feng W X, Tong X F, LI X L. Analysis of lightning parameters and weak sections for 1000 kV UHV transmission line corridor[J]. High Voltage Engineering, 2006, 32(12):45-48. (in Chinese)
[3] 陈家宏,谷山强,李晓岚,童雪芳. 1000 kV特高压交流试验示范工程线路走廊雷电分布特征研究[J]. 中国电力,2007, 40(12):27-30. Chen J H, Gu S Q, Li X L, Tong X F. Analysis of lightning distribution characteristics for 1000 kVUHVAC transmission line corridor[J]. Electric Power, 2007, 40(12):27-30. (in Chinese)
[4] 谷山强,陈家宏,陈维江,李晓岚,童雪芳,张瑞. 输电线路防雷性能时空差异化评估方法[J]. 高电压技术,2009, 35(2):294-298. Gu S Q, Chen J H, Chen W J, LI X L, Tong X F, Zhang R. Evaluation method of the time-space-difference of lightning protection performance of transmission lines[J]. High Voltage Engineering, 2009, 35(2):294-298. (in Chinese)
[5] 郭三刚,龚静,何生存. 青海东北部地区雷电活动的时空分布特征[J]. 青海科技,2005(6):22-25. Guo S G, Gong J, He S C. Spatial and temporal distribution of lightning activity in the northeastern part of Qinghai province[J]. Qinghai Science and Technology, 2005(6):22-25. (in Chinese)
[6] 尹丽云,许迎杰,张腾飞,邓勇,刘雪涛,谢屺然,徐开. 一种新的雷电日及雷电参数统计方法[J]. 气象科技,2009, 37(6):739-744. Yi Y L, Xu Y J, Zhang T F, Deng Y, Liu X T, Xie Q R, Xu K. A new statistical method of lightning days and lightning parameters[J]. Meteorological Science and Technology, 2009, 37(6):739-744. (in Chinese)
[7] 赵伟,童杭伟,张俊,浦静娇. 浙江省雷电时空分布特征及影响因素分析[J]. 电网技术,2013, 37(5):1425-1431. Zhao W, Tong H W, Zhang J, Pu J J. Temporal -spatial distribution characteristics of thunder and lightning in Zhejiang province and influencing factors[J]. Power System Technology, 2013, 37(5):1425-1431. (in Chinese)
[8] 赵超,舒红,朱欣焰,戴上平. 气象数据概化中的最佳聚类数研究[J]. 华中师范大学学报(自然科学版), 2008(3):490-493. Zhao C, Shu H, Zhu X Y, Dai S P. Determination of the optimal class number in meteorological data generalization[J]. Journal of Huazhong Normal University (Natural Science Edition), 2008(3):490-493. (in Chinese)
[9] 赵海波. 基于GIS的城市气象监测要素插值分析研究[D]. 云南:昆明理工大学,2010.
[10] 陈勇伟,郑涛,王汉堃,王琦,梁耀丹. 基于BP神经网络模型的雷电潜势预报[J]. 干旱气象,2013, 31(3):595-601. Chen Y W, Zheng T, Wang H K, Wang Q, Liang Y D. Thunderstorm potential prediction based on back propagation neural network[J]. Journal of Arid Meteorology, 2013, 31(3):595-601. (in Chinese)
[11] Koperski K, Han J. Discovery of spatial association rules in geographic information databases,[C]//4th International Symposium SSD'95 Portlanal, ME, USA, August 6-9, 1995.
[12] Han J, Kamber M, Pei J. Data mining:concepts and techniques:concepts and techniques[M].[S.l.]:Elsevier Science, 2011.
[13] 张玲玲,周全亮,唐广文,李兴森,石勇. 基于领域知识和聚类的关联规则深层知识发现研究[J]. 中国管理科学,2015, 23(1):154-161. Zhang L L, Zhou Q L, Tang G W, Li X S, Shi Y. Research on algorithm of post-processing association rules based on clustering and domain knowledge[J]. Chinese Journal of Management Science, 2015, 23(1):154-161. (in Chinese)
[14] 魏峰. 基于聚类的关联规则挖掘算法研究[D]. 杭州:浙江工业大学,2012.
/
| 〈 |
|
〉 |
