|本期目录/Table of Contents|

[1]吴海波,施式亮,念其锋.基于Spark Streaming流回归的煤矿瓦斯浓度实时预测[J].中国安全生产科学技术,2017,13(5):84-89.[doi:10.11731/j.issn.1673-193x.2017.05.014]
　WU Haibo,SHI Shiliang,NIAN Qifeng.Real-time prediction of gas concentration in coal mine based on Spark Streaming Linear Regression[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(5):84-89.[doi:10.11731/j.issn.1673-193x.2017.05.014]
点击复制

基于Spark Streaming流回归的煤矿瓦斯浓度实时预测
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
13
期数:
2017年5期
页码:
84-89
栏目:
现代职业安全卫生管理与技术
出版日期:
2017-05-31

文章信息/Info

Title:
Real-time prediction of gas concentration in coal mine based on Spark Streaming Linear Regression
文章编号:
1673-193X(2017)-05-0084-06
作者:
吴海波1; 2 ;  施式亮1; 3 ;  念其锋2; 4
1.中南大学 资源与安全工程学院, 湖南 长沙 410083；2.湖南科技大学 计算机科学与工程学院，湖南 湘潭 411201；3.湖南科技大学 资源环境与安全工程学院，湖南 湘潭 411201；4.湖南科技大学煤炭资源清洁利用与矿山环境保护湖南省重点实验室，湖南 湘潭 411201
Author(s):
WU Haibo1; 2;  SHI Shiliang1; 3;  NIAN Qifeng2; 4
1. School of Resource & Safety Engineering, Central Southern University, Changsha Hunan 410083, China; 2. School of Computer Science & Engineering, Hunan University of Science & Technology, Xiangtan Hunan 411201, China; 3. School of Resource Environment & Safety Engineering, Hunan University of Science & Technology, Xiangtan Hunan 411201, China; 4. Hunan Province Key Laboratory of Coal Resources Clean-utilization and Mine Environment Protection, Xiangtan Hunan 411201, China
关键词:
监测数据; 流数据; 瓦斯浓度; Spark Streaming; 流回归; 实时预测; 灾害预警
Keywords:
monitoring data;  streaming data;  gas concentration;  Spark Streaming;  Streaming Linear Regression;  real-time prediction;  disaster warning
分类号:
X936
DOI:
10.11731/j.issn.1673-193x.2017.05.014
文献标志码:
A
摘要:
为了实时分析瓦斯监测流数据并对瓦斯浓度进行准确预测以实现瓦斯灾害实时预警，以实时流数据处理框架Spark Streaming构建基于流回归的瓦斯浓度实时预测系统。系统采用分布式流处理技术，可使基于回归算法的瓦斯浓度预测模型更新周期达到秒级，提高了瓦斯浓度预测精度，满足流式大数据处理的实时性要求。实验表明:应用Spark Streaming流回归预测系统在采样周期为5 s的瓦斯监测数据流上进行实时预测时，预测平均均方根误差随模型更新周期的缩短而减小，模型更新周期可达15 s，且更新周期为45 s时预测总均方根误差最小，既能保证预测精度，又能提高瓦斯灾害预警时效。
Abstract:
In order to analyze the streaming data of gas monitoring in real-time and predict the gas concentration accurately, so as to achieve the real-time warning of gas disaster, a real-time prediction system of gas concentration based on Streaming Linear Regression was constructed by using the real-time streaming data processing framework Spark Streaming. The system adopted the distributed stream processing technology, which could make the update cycle of the gas concentration prediction model based on regression algorithm reach the second level, improve the prediction accuracy of gas concentration, and meet the real-time requirement of streaming large data processing. The experiments showed that when applying the predicting system based on Spark Streaming Linear Regression to carry out the real-time prediction on the gas monitoring data stream with the sampling cycle of 5 seconds, the average root-mean-square error (RMSE) of prediction decreased with the shortening update cycle of the model. The update cycle of the model could reach 15 seconds, and the total RMSE was the smallest when the update cycle was 45 seconds, which can ensure the accuracy of prediction, and improve the warning timeliness of gas disaster.

参考文献/References:

［1］张剑英, 程健, 侯玉华, 等. 煤矿瓦斯浓度预测的ANFIS方法研究［J］. 中国矿业大学学报, 2007, 36(4):494-498. ZHANG Jianying, CHENG Jian, HOU Yuhua，et al． Forecasting coalmine gas concentration based on adaptive neuro-fuzzy inference system［J］. Journal of China University of Mining& Technology, 2007, 36(4):494-498.
［2］杨丽, 刘晖, 毛善君, 等. 基于多元分布滞后模型的瓦斯浓度动态预测［J］. 中国矿业大学学报, 2016, 45(3):455-461. YANG Li, Liu Hui, MAO Shanjun, et al. Dynamic prediction of gas concentration based on multivariate distribution lag model［J］. Journal of China University of Mining & technology, 2016, 45(3):455-461.
［3］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.
［4］张宝燕, 李茹, 穆文瑜. 基于混沌时间序列的瓦斯浓度预测研究［J］. 计算机工程与应用, 2011, 47(10):244-248. ZHANG Baoyan, LI Ru, MU Wenyu. Study on gas concentration prediction based on chaotic time series［J］. Computer Engineering and Applications, 2011,47(10):244-248.
［5］刘俊娥, 杨晓帆, 郭章林. 基于FIG-SVM的煤矿瓦斯浓度预测［J］. 中国安全科学学报, 2013, 23(2):80-84. LIU June, YANG Xiaofan, GUO Zhanglin. Prediction of coal mine gas concentration based on FIG-SVM［J］. China Safety Science Journal, 2013, 23(2):80-84.
［6］付华, 丰盛成, 刘晶, 等. 基于DE-EDA-SVM的瓦斯浓度预测建模仿真研究［J］. 传感技术学报, 2016, 29(2):285-289. FU Hua, FENG Shengcheng, LIU Jing, et al. The modeling and simulation of gas concentration prediction based on De-Eda-Svm［J］. Chinese Journal of Sensors and Actuators, 2016, 29(2):285-289.
［7］郭瑞, 徐广璐. 基于信息融合与GA-SVM的煤矿瓦斯浓度多传感器预测模型研究［J］. 中国安全科学学报, 2013, 23(9):33-38. GUO Rui, XU Guanglu. Research on coal mine gas concentration multi-sensor prediction model based on information fusion and GA-SVM［J］. China Safety Science Journal, 2013, 23(9):33-38.
［8］穆文瑜, 李茹. 基于K-Means聚类的瓦斯浓度预测［J］. 计算机应用, 2011, 31(3):702-705. MU Wenyu, LI Ru. Prediction of gas concentration based on K-Means clustering［J］. Journal of Computer Applications, 2011, 31(3):702-705.
［9］彭程, 潘玉民. 粒子群优化的RBF瓦斯涌出量预测［J］. 中国安全生产科学技术, 2011, 7(11):77-81. PENG Cheng, PAN Yumin. Particleswarm optimization RBF for gas emission prediction［J］. Journal of Safety Science and Technology, 2011, 7(11):77-81.
［10］曹博, 白刚, 李辉. 基于PCA-GA-BP神经网络的瓦斯含量预测分析［J］. 中国安全生产科学技术, 2015, 11(5):84-90. CAO Bo, BAI Gang, LI Hui. Prediction of gas content based on PCA-GA-BP neural network［J］. Journal of Safety Science and Technology, 2015, 11(5):84-90.
［11］刘奕君, 赵强, 郝文利. 基于遗传算法优化BP神经网络的瓦斯浓度预测研究［J］. 矿业安全与环保, 2015, 42(2):56-60. LIU Yijun, ZHAO Qiang, HAO Wenli. Study of gas concentration prediction based on genetic algorithm and optimizing BP neural network［J］. Mining Safety & Environmental Protection, 2015,42(2):56-60.
［12］唐亮, 李春生, 许虎, 等. 基于BP和RBFNN的神经网络算法在瓦斯预测中的应用及比较［J］. 中国安全生产科学技术, 2007, 3(6):31-34. TANG Liang, LI Chunsheng, XU Hu, et al. The application and comparison of neural network based on algorithm BP and RBFNN in methane prediction［J］. Journal of Safety Science and Technology, 2007, 3(6):31-34.
［13］胡俊, 胡贤德, 程家兴. 基于Spark的大数据混合计算模型［J］. 计算机系统应用, 2015, 24(4):214-218. HU Jun, HU Xiande, CHEN Jiaxing. Big data hybrid computing mode based on spark［J］. Computer Systems and Applications, 2015, 24(4):214-218.
［14］Matei Zaharia, Tathagata Das, Haoyuan Li, et al.Discretized streams: fault-tolerant streaming computation at scale［A］. Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles［C］. Farmington, PA, November 03-06, 2013.
［15］Bar N, Ule G. Streaming Linear Regression on Spark MLlib and MOA［A］. Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining Paris France［C］. August 25-28, 2015.

相似文献/References:

[1]孙廉威,张阿晋,吴小建.窄长类匝道基坑开挖变形监测数据统计分析*[J].中国安全生产科学技术,2021,17(5):93.[doi:10.11731/j.issn.1673-193x.2021.05.014]
　SUN Lianwei,ZHANG Ajin,WU Xiaojian.Statistical analysis on deformation monitoring data in excavation of narrow and long ramp foundation pit[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(5):93.[doi:10.11731/j.issn.1673-193x.2021.05.014]
[2]张宇航,戎思达,李慧,等.基于动态监测与事故树分析的超大深基坑风险分析方法研究*[J].中国安全生产科学技术,2023,19(9):89.[doi:10.11731/j.issn.1673-193x.2023.09.013]
　ZHANG Yuhang,RONG Sida,LI Hui,et al.Research on risk analysis method of super-large deep foundation pit based on dynamic monitoring and fault tree analysis[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(5):89.[doi:10.11731/j.issn.1673-193x.2023.09.013]

备注/Memo

备注/Memo:
煤矿安全开采技术湖南省重点实验室开放基金项目（201304）；湖南省高等学校科学研究优秀青年项目（14B058）；湖南科技大学煤炭资源清洁利用与矿山环境保护湖南省重点实验室开放基金项目（E21701）
更新日期/Last Update: 2017-06-09