基于大数据的瓦斯报警甄别研究
|
摘要
瓦斯报警的正确性和准确性是煤矿安全生产的重大问题。煤矿安全监控系统实时对井下环境进行检测,每天产生大量数据,用传统方法不能准确快速地甄别出瓦斯突出、异常数据或者传感器正常标校的情况。为此,利用基于时间序列的大数据挖掘技术,研究了煤矿安全生产中瓦斯报警问题,解决了传统人工识别方法不能快速甄别瓦斯报警类型等难题。详细论述了时间序列的大数据挖掘技术,针对煤矿的具体情况建立了相关的数学模型,并将系统用于平煤神马集团。实用表明,对瓦斯报警的甄别达到了比较高的准确率,较好地解决了瓦斯报警数据的甄别问题。
The correctness and veracity of the gas alarms are the major problems in the safe production of coal mines.The Coal mine safety monitoring system detects the underground environment in real time and generates large amounts of data every day. The traditional method can not accurately and quickly identify the gas outburst, abnormal data or normal calibration of the sensor. Therefore, the big data mining technology based on time series was used to identify the types of gas quickly to solve the problem of gas alarm in coal mine safety production.The big data mining technology of time series was discussed in detail.According to the specific situation of coal mine,the relevant mathematical model was established and applied to PingMei ShenMa Group.The practical results show that the identification has reached a relatively high accuracy rate,which solves the problem of the screening of gas alarm data.
The correctness and veracity of the gas alarms are the major problems in the safe production of coal mines.The Coal mine safety monitoring system detects the underground environment in real time and generates large amounts of data every day. The traditional method can not accurately and quickly identify the gas outburst, abnormal data or normal calibration of the sensor. Therefore, the big data mining technology based on time series was used to identify the types of gas quickly to solve the problem of gas alarm in coal mine safety production.The big data mining technology of time series was discussed in detail.According to the specific situation of coal mine,the relevant mathematical model was established and applied to PingMei ShenMa Group.The practical results show that the identification has reached a relatively high accuracy rate,which solves the problem of the screening of gas alarm data.
引文
[1]孙继平,王福增.煤矿井下电磁干扰对通信和监控系统的影响分析[J].工况自动化,2009,35(2):23-27.
[2]曲文龙.复杂时间序列知识发现模型与算法研究[D].北京:北京科技大学,2006.
[3]欧阳为民,蔡庆生.数据库中的时态数据发掘研究[J].计算机科学,1998,25(4):60-63.
[4]安鸿志,陈兆国,杜金观,等.时间序列的分析与应用[M].北京:科学出版社,1983.
[5]李瑶,蒋觉义.小波与时间序列在数字信号质量监测中的应用[J].测控技术,2014,33(12):20-23.
[6]马雪婧,朱杰,王直,等.基于主元的多元时间序列聚类分析方法研究[J].测控技术,2012,31(12):104-107.
[7] Pavlidis T,Horwitz S L.Segmentation of plane curves[J].IEEE Transactions on Computers,1974,C-23(8):860-870.
[8] Park S,Kim S W,Chu W W. Segment-based approach for subsequence searches in sequence databases[C]//Proceedings of the 16th ACM Symposium on Applied Computing.2001:248-252.
[9] Park S,Lee D,Chu W W. Fast retrieval of similar subsequences in long sequence databases[C]//Proceedings of the1999 Workshop on Knowledge and Data Engineering Exchange.1999:60-67.
[10] Pratt K B,Fink E.Search for patterns in compressed time series[J]. International Journal of Image and Graphics,2002,2(1):89-106.
[11] Xiao H,Feng X F,Hu Y F.A new segmented time warping distance for data mining in time series database[C]//Proceedings of 2004 International Conference on Machine Learning and Cybernetics.2004:1277-1281.
[12]郭小芳,李锋,王卫东.基于k-近邻的多元时间序列局部异常检测[J].江苏科技大学学报(自然科学版),2012,26(5):505-509.
[13]孙焱,林意.基于相似性分析的时间序列异常检测方法[J].山东农业大学学报(自然科学版),2017,48(2).
[2]曲文龙.复杂时间序列知识发现模型与算法研究[D].北京:北京科技大学,2006.
[3]欧阳为民,蔡庆生.数据库中的时态数据发掘研究[J].计算机科学,1998,25(4):60-63.
[4]安鸿志,陈兆国,杜金观,等.时间序列的分析与应用[M].北京:科学出版社,1983.
[5]李瑶,蒋觉义.小波与时间序列在数字信号质量监测中的应用[J].测控技术,2014,33(12):20-23.
[6]马雪婧,朱杰,王直,等.基于主元的多元时间序列聚类分析方法研究[J].测控技术,2012,31(12):104-107.
[7] Pavlidis T,Horwitz S L.Segmentation of plane curves[J].IEEE Transactions on Computers,1974,C-23(8):860-870.
[8] Park S,Kim S W,Chu W W. Segment-based approach for subsequence searches in sequence databases[C]//Proceedings of the 16th ACM Symposium on Applied Computing.2001:248-252.
[9] Park S,Lee D,Chu W W. Fast retrieval of similar subsequences in long sequence databases[C]//Proceedings of the1999 Workshop on Knowledge and Data Engineering Exchange.1999:60-67.
[10] Pratt K B,Fink E.Search for patterns in compressed time series[J]. International Journal of Image and Graphics,2002,2(1):89-106.
[11] Xiao H,Feng X F,Hu Y F.A new segmented time warping distance for data mining in time series database[C]//Proceedings of 2004 International Conference on Machine Learning and Cybernetics.2004:1277-1281.
[12]郭小芳,李锋,王卫东.基于k-近邻的多元时间序列局部异常检测[J].江苏科技大学学报(自然科学版),2012,26(5):505-509.
[13]孙焱,林意.基于相似性分析的时间序列异常检测方法[J].山东农业大学学报(自然科学版),2017,48(2).
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |