基于Hadoop平台的瓦斯突出预测预警方法研究*

doi:10.16265/j.cnki.issn1003-3033.2017.11.011

中国安全科学学报 ›› 2017, Vol. 27 ›› Issue (11): 61-66.doi: 10.16265/j.cnki.issn1003-3033.2017.11.011

基于Hadoop平台的瓦斯突出预测预警方法研究^*

郝天轩^1,2,3 教授, 张春林²

1 河南省瓦斯地质与瓦斯治理重点实验室—省部共建国家重点实验室培育基地,河南焦作 454000
2 河南理工大学安全科学与工程学院,河南焦作 454000
3 煤炭安全生产河南省协同创新中心,河南焦作 454000

收稿日期:2017-08-15 修回日期:2017-10-10 发布日期:2020-10-21
作者简介:郝天轩 (1976—),男,河南孟州人,博士,教授,主要从事矿山安全及数字化、信息化等方面的研究。E-mail:htx@hpu.edu.cn。
基金资助:
河南科技攻关项目(172102310474);河南省基础与前沿技术研究计划(142300413233);教育部创新团队发展支持计划(IRT_16R22)。

Study on Hadoop platform based method for gas outburst prediction and early warning

HAO Tianxuan^1,2,3, ZHANG Chunlin²

1 State Key Laboratory Cultivation Base for Gas Control Co-founded by Henan Province and the Ministry of Science and Technology,Jiaozuo Henan 454000,China
2 College of Safety Science and Engineering, Henan Polytechnic University,Jiaozuo Henan 454000,China
3 Henan Province Co-Innovation Coal Safety Production,Jiaozuo Henan 454000,China

Received:2017-08-15 Revised:2017-10-10 Published:2020-10-21

摘要/Abstract

摘要： 为防治煤与瓦斯(甲烷)突出事故,提出基于Hadoop平台的煤与瓦斯突出预测预警方法。首先,选用霍尔特指数平滑法对实时监测的瓦斯体积分数数据进行预处理,以提高监测数据的准确性和完整性;其次,基于BP神经网络模型,提取监测的瓦斯体积分数的特征参数,并结合人工检测的防突检测参数,构建瓦斯突出预测预警模型;最后,在平煤八矿戊9-10-21050工作面,进行现场应用,验证该方法的可行性。研究表明:用该方法能较好地处理及分析海量瓦斯体积分数所得数据,突出预测预警结果可靠性较高,能够满足现场实际应用的需要。

关键词: Hadoop平台, 监/检测数据, 矿井瓦斯, 预警, 煤与瓦斯突出

Abstract: In order to prevent coal and gas (methane) outburst accidents, this paper was aimed at working out a method for prediction and early warning of coal and gas outburst based on Hadoop platform. Firstly, the Holt exponential smoothing method was used for preprocessing the gas concentration monitoring data in real time, so as to improve the accuracy and integrity of the monitoring data. Secondly, characteristic parameters of the gas concentration were extracted based on the BP neural network model. A gas outburst prediction and early warning model was built on the basis of both characteristic parameters extracted and the outburst prevention detection data. Finally, field application of the method was made at the Wu9-10-21050 working face of Pingdingshan No.8 mine. The results show that the method can be used for dealing with and analyzing large quantities of gas concentration data, improving the reliability of both the prediction and the early warning.

Key words: Hadoop platform, monitoring data, coal mine gas, early warning, coal and gas outburst

中图分类号:

X936

郝天轩教授, 张春林. 基于Hadoop平台的瓦斯突出预测预警方法研究^*[J]. 中国安全科学学报, 2017, 27(11): 61-66.

HAO Tianxuan, ZHANG Chunlin. Study on Hadoop platform based method for gas outburst prediction and early warning[J]. China Safety Science Journal, 2017, 27(11): 61-66.

参考文献

[1] 聂百胜, 何学秋, 王恩元, 等. 煤与瓦斯突出预测技术研究现状及发展趋势[J]. 中国安全科学学报, 2003,13(6):40-43.
NIE Baisheng, HE Xueqiu, WANG Enyuan, et al. Present situation and progress trend of prediction technology of coal and gas outburst[J]. China Safety Science Journal, 2003,13(6):40-43.
[2] 秦汝祥, 张国枢, 杨应迪. 瓦斯浓度序列的煤与瓦斯突出预报方法及应用[J]. 安徽理工大学学报:自然科学版, 2008,28(1):25-29.
QIN Ruxiang, ZHANG Guoshu, YANG Yingdi. Method of coal and gas outburst forecast by sequence of gas concentration and its application[J]. Journal of Anhui University of Science and Technology:Natural Science, 2008,28(1):25-29.
[3] 孙丽娟. 基于煤矿瓦斯监测数据的煤与瓦斯突出预警技术研究[D]. 焦作:河南理工大学, 2010.
SUN Lijuan. Research on warning technology of coal and gas outburst based on methane monitoring data[D]. Jiaozuo: Henan Polytechnic University, 2010.
[4] 邓明, 张国枢, 陈清华. 基于瓦斯涌出时间序列的煤与瓦斯突出预报[J]. 煤炭学报, 2010,35(2):260-263.
DENG Ming, ZHANG Guoshu, CHEN Qinghua. Forecast of coal and gas outburst based on time series of gas concentration[J]. Journal of China Coal Society, 2010,35(2):260-263.
[5] WANG Chao, WANG Enyuan, XU Jiankun. Bayesian discriminant analysis for prediction of coal and gas outbursts and application [J]. Mining Science and Technology (China), 2010,20(4):520-523.
[6] 陈志华. 基于Hadoop的神经网络算法在网络学习评价中的应用研究[J]. 计算机与数字工程, 2016,44(2): 248-251.
CHEN Zhihua. Application of Hadoop-based neural network algorithm in E-learning evaluation study [J]. Computer & Digital Engineering, 2016,44(2): 248-251.
[7] 欧阳秋梅, 吴超, 黄浪. 大数据应用于安全科学领域的基础原理研究[J]. 中国安全科学学报, 2016,26(11): 13-18.
OUYANG Qiumei, WU Chao, HUANG Lang. Research on basic principles of applications of big data in field of safety science[J]. China Safety Science Journal, 2016,26(11): 13-18.
[8] 董丁稳. 基于安全监控系统实测数据的瓦斯浓度预测预警研究[D]. 西安:西安科技大学, 2012.
DONG Dingwen. Study on gas concentration prediction and early warning based on real'time monitoring data of safety monitoring system[D]. Xi'an: Xi'an University of Science and Technology, 2012.
[9] 陈光. 霍特指数平滑法参数的优选[J]. 统计与决策, 2005(8):27-28.
[10] 张海军. 基于云计算的神经网络并行实现及其学习方法研究[D]. 广州: 华南理工大学,2015.
ZHANG Haijun. Research on parallel implementation of neural networks based on cloud computing and their learning methods[D]. Guangzhou: South China University of Technology, 2015.

[1]	曾纪涵, 章光, 吴浩, 胡少华. 改进POT模型下尾矿坝综合预警值确定方法[J]. 中国安全科学学报, 2022, 32(5): 134-139.
[2]	李超, 邓小宝, 史运涛, 孙德辉, 焦彦宗. 社区户内燃气泄漏动态预警模型[J]. 中国安全科学学报, 2022, 32(3): 90-97.
[3]	冯巩, 夏元友, 王智德, 严敏嘉. 基于位移信息融合的露天矿边坡动态预警方法[J]. 中国安全科学学报, 2022, 32(3): 116-122.
[4]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型^*[J]. 中国安全科学学报, 2022, 32(1): 27-33.
[5]	张进春, 陈昕, 张文俊, 吴士龙. 基于广义极值分布的流化床压力波动风险预警^*[J]. 中国安全科学学报, 2022, 32(1): 85-91.
[6]	张巨峰, 施式亮, 鲁义, 游波, 吴芳华, 吴宽. 大数据下瓦斯与煤自燃共生灾害智能预警系统:数据特征、应用架构、关键技术^*[J]. 中国安全科学学报, 2021, 31(9): 60-66.
[7]	张充, 赵挺生, 蒋灵, 王鑫, 唐菁菁. 塔式起重机结构安全监测参数选取及测点布置^*[J]. 中国安全科学学报, 2021, 31(8): 112-118.
[8]	沈阳, 徐磊, 王少纯. 基于风险管理的整体钢平台变形预警指标研究[J]. 中国安全科学学报, 2021, 31(6): 56-63.
[9]	隆能增, 袁梅, 王关亮, 王清辉, 许石青, 李鑫灵. 煤与瓦斯突出微震-瓦斯互动响应预警研究[J]. 中国安全科学学报, 2021, 31(4): 125-132.
[10]	李继超, 郭聖煜, 孔刘林, 原毅璨, 孙阳. 施工现场火焰检测和预警机器人设计及应用[J]. 中国安全科学学报, 2021, 31(4): 141-146.
[11]	谭波, 邵壮壮, 郭岩, 赵彤, 朱红青, 李传兴. 基于指标气体关联分析的煤自燃分级预警研究[J]. 中国安全科学学报, 2021, 31(2): 33-39.
[12]	刘同宇, 李师, 付卫东, 段强领, 孙金华, 王青松. 大容量磷酸铁锂动力电池热失控预警策略研究^*[J]. 中国安全科学学报, 2021, 31(11): 120-126.
[13]	郑晓亮, 来文豪, 薛生. MI和SVM算法在煤与瓦斯突出预测中的应用[J]. 中国安全科学学报, 2021, 31(1): 75-80.
[14]	宋大钊, 何学秋, 窦林名, 祖自银, 王安虎, 李振雷. 煤层突出危险微震区域探测技术研究[J]. 中国安全科学学报, 2021, 31(1): 89-94.
[15]	贾宝峰, 阎美好. 铁路快运货物安全预警系统研究[J]. 中国安全科学学报, 2020, 30(S1): 121-127.

基于Hadoop平台的瓦斯突出预测预警方法研究^*

Study on Hadoop platform based method for gas outburst prediction and early warning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价