[1]李伟山,王 琳,卫 晨.LSTM在煤矿瓦斯预测预警系统中的应用与设计[J].西安科技大学学报,2018,(06):1027-1035.[doi:10.13800/j.cnki.xakjdxxb.2018.0621]
 LI Wei-shan,WANG Lin,WEI Chen.Application and design of LSTM in coal mine gas prediction and warning system[J].Journal of Xi'an University of Science and Technology,2018,(06):1027-1035.[doi:10.13800/j.cnki.xakjdxxb.2018.0621]
点击复制

LSTM在煤矿瓦斯预测预警系统中的应用与设计(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2018年06期
页码:
1027-1035
栏目:
出版日期:
2018-11-30

文章信息/Info

Title:
Application and design of LSTM in coal mine gas prediction and warning system
文章编号:
1672-9315(2018)06-1027-09
作者:
李伟山1王 琳1卫 晨2
(1.西安邮电大学 通信与信息工程学院,陕西 西安 710121; 2.西安邮电大学 经济与管理学院,陕西 西安 710121)
Author(s):
LI Wei-shan1WANG Lin1WEI Chen2
(1.School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China; 2.School of Economics and Management,Xi'an University of Posts and Telecommunications,Xi'an 710121,China)
关键词:
瓦斯预测预警系统 神经网络 长短时记忆网络
Keywords:
gas prediction and warning system neural network long short time memory
分类号:
TP 391
DOI:
10.13800/j.cnki.xakjdxxb.2018.0621
文献标志码:
A
摘要:
针对煤矿瓦斯浓度的预测的问题,以亭南煤矿正常生产期间302工作面的监测数据为研究背景,采用深度学习技术LSTM(Long Short Time Memory,长短时记忆网络)建立瓦斯预测模型,研究与设计了基于LSTM的煤矿瓦斯预测预警系统。LSTM网络针对时间序列数据具有较强的建模能力,能够实现信息的长期依赖,自动挖掘数据之间潜在的关联关系。采集煤矿正常生产期间的瓦斯监测数据作为训练数据,利用深度学习框架TensorFlow进行算法的仿真,并研究了不同时间步长、网络深度下的LSTM以及多信息融合对瓦斯预测模型性能的影响。实验结果在1 000条测试数据集上获得了3.61%平均相对偏差,LSTM瓦斯预测模型具有较高的准确度,泛化能力强。在系统研究与设计中,使用Spring,SpringMVC和Hibernate框架按照适应性、易用性、可扩展性等原则对系统进行了设计。系统部署阶段,将训练好的LSTM瓦斯预测模型部署在TensorFlow Serving服务器中,对外提供服务,实现了煤矿瓦斯预警系统,增强了煤矿瓦斯监控系统的预警能力,提高了煤炭企业安全生产管理水平,具有一定的实用价值。
Abstract:
In order to solve the problem of prediction of coal mine gas concentration,taking the monitoring data of the 302face during the normal production period of Tingnan Coal Mine as research background,using deep learning technology LSTM to establish the model of gas prediction,a coal mine gas prediction and early warning system based on LSTM(Long Short Time Memory)is designed.LSTM has strong modeling ability regarding time-series data,can realize the long-term dependence on information and automatically excavate the potential relationship between data.Collecting the gas monitoring data during the normal production of the coal mine as training data,the TensorFlow deep learning framework is used to simulate the coal mine gas prediction model.The effects of different time steps,network depth and multi-information fusion on the performance of the model are studied.The experimental results show an average relative deviation of 3.61% on 1000test datasets.The LSTM gas prediction model has high accuracy with strong generalization ability.In system research and design phase,the system is designed using Spring,SpringMVC and hibernate frameworks according to the principles of adaptability,ease of use,and scalability.In system deployment phase,the trained LSTM gas forecasting model is deployed in the server to provide services to the outside world,to realize the coal mine gas warning system,enhance the early warning capability of the coal mine gas monitoring system and improve the safety management of the coal mining enterprises.

参考文献/References:


[1] 宋振骐,文志杰.煤炭资源的开采现状及发展方向[J].科技导报,2011,29(35):3-6. SONG Zhen-qi,WEN Zhi-jie.Current situation and development direction of coal resources exploitation[J].Science and Technology Review,2011,29(35):3-6.
[2]宁德义.我国煤矿瓦斯防治技术的研究进展及发展方向[J].煤矿安全,2016,47(2):161-165. NING De-yi.Research progress and development trend of coal mine gas prevention technology in China[J].Safety in Coal Mines,2016,47(2):161-165.
[3]张昭昭,乔俊飞,余 文.基于动态神经网络的瓦斯浓度实时预测方法[J].控制工程,2016,23(4):478-483. ZHANG Zhao-zhao,QIAO Jun-fei,YU Wen.Forecasting coalmine gas concentration based on dynamic neural network[J].Control Engineering of China,2016,23(4):478-483.
[4]赵爱蓉.基于小波分析及BP神经网络的瓦斯浓度预测方法研究[J].煤矿机械,2014,35(6):258-260. ZHAO Ai-rong.Prediction method of gas concentration based on wavelet analysis and BP neural network[J].Coal Mine Machinery,2014,35(6):258-260.
[5]郝天轩,李鹏飞.基于灰色关联分析-GA-BP模型预测煤层瓦斯含量[J].中国矿业,2016(11):116-120. HAO Tian-xuan,LI Peng-fei.Prediction of gas content based on gray correlation analysis -GA-BP neural network[J].China Mining Magazine,2016(11):116-120.
[6]韩婷婷,吴世跃,王鹏军.基于马尔科夫残差修正的瓦斯浓度预测[J].工矿自动化,2014,40(3):28-31. HAN Ting-ting,WU Shi-yue,WANG Peng-jun.Prediction of gas concentration based on residual correction of Markov chain[J].Industry and Mine Automation,2014,40(3):28-31.
[7]刘 翔,杨 帆.基于数据挖掘技术的瓦斯灾害信息特征提取[J].煤炭技术,2016,35(8):130-132. LIU Xiang,YANG Fan.Information feature extraction of gas disaster based on data mining technology[J].Coal Technology,2016,35(8):130-132.
[8]Sak H,Senior A,Beaufays F.Long short term memory based recurrent neural network architectures for large vocabulary speech recognition[J].Computer Science,2014,13:338-342.
[9]Sundermeyer M,Schlüter R,Ney H.LSTM neural networks for Language modeling[J].Interspeech,2012,31(43):601-608.
[10]Gers F A,Eck D,Schmidhuber J.Applying LSTM to time series predictable through time-window approaches[C]//International Conference on Artificial Neural Networks.Springer-Verlag,2001:669-676.
[11]Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[C]//Advances in Neural Information Processing Systems,2017:6000-6010.
[12]Liu C,Wang C,Sun F,et al.Image 2 text:a multimodal image captioner[C]//ACM on Multimedia Conference.ACM,2016:746-748.
[13]黄光许,田 垚,康 健,等.低资源条件下基于I-vector特征的LSTM递归神经网络语音识别系统[J].计算机应用研究,2017,34(2):392-396. HUANG Guang-xu,TIAN Yao,KANG Jian,et al.Long short term memory recurrent neural network acoustic models using I-vector for low resource speech recognition[J].Application Research of Computers,2017,34(2):392-396.
[14]杨训政,柯余洋,梁 肖,等.基于 LSTM的发电机组污染物排放预测研究[J].电气自动化,2016,38(5):22-25. YANG Xun-zheng,KE Yu-yang,LIANG Xiao,et al.A study on the prediction of generator set pollutant emissions based on LSTM[J].Electrical automation,2016,38(5):22-25.
[15]Schmidhuber J.Deep Learning in neural networks:an overview[J].Neural Networks,2015,61:85-117.
[16]Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436.
[17]Hochreiter S,Schmidhuber J.Long short term memory[J].Neural Computation,1997,9(8):1735.
[18]魏连江,梁 伟,高金晓,等.矿井瓦斯监测数据趋势预测研究进展[J].煤矿安全,2016,47(10):149-152. WEI Lian-jiang,LIANG Wei,GAO Jin-xiao,et al.Research progress on trend prediction of mine gas monitoring data[J].Safety in Coal Mines,2016,47(10):149-152.
[19]Diederik P Kingma,Jimmy Lei Ba.Adam:a method for stochatic optimization[J].ArXiv Preprint ArXiv,2015,1412(8):69-80.
[20]Olston C,Fiedel N,Gorovoy K,et al.Tensor flow-serving:flexible,high-performance ML serving[J].ArXiv Preprint ArXiv,2017,1712(6):139.
[21]Abadi M,Barham P,Chen J,et al.TensorFlow:a system for large-scale machine learning[C]//OSDI,2016,16:265-283.
[22]张 飞,张 建.基于Spring与Hibernate的数据库访问技术研究[J].计算机工程与设计,2009,30(7):1668-1670. ZHANG Fei,ZHANG Jian.Research on database access technology based on Spring and Hibernate[J].Computer Engineering and Design,2009,30(7):1668-1670.
[23]黄 淼,王刘涛.基于MVC的煤矿瓦斯预警系统开发[J].信息技术,2016(6):88-92. HUANG Miao,WANG Liu-tao.Development of coal mine gas early warning system based on MVC[J].Information Technology,2016(6):88-92.
[24]薛 峰,梁 锋,徐书勋,等.基于Spring MVC框架的Web研究与应用[J].合肥工业大学学报,2012,35(3):337-340. XUE Feng,LIANG Feng,XU Shu-xun,et al.Research on springMVC framework based Web and its application[J].Journal of Hefei University of Technology,2012,35(3):337-340.
[25]华 涛,郝克刚,葛 玮.基于Hibernate和Spring框架的Web应用研究[J].计算机技术与发展,2006,16(11):84-86. HUA Tao,HAO Ke-gang,GE Wei.Web research based on Hibernate and Spring frameworks[J].Computer Technology and Development,2006,16(11):84-86.

相似文献/References:

[1]龚尚福,李岩松.基于数据融合的井下瓦斯浓度状态预测[J].西安科技大学学报,2018,(03):506.[doi:10.13800/j.cnki.xakjdxxb.2018.0323]
 GONG Shang-fu,LI Yan-song.Prediction of underground gas concentration state based on data fusion[J].Journal of Xi'an University of Science and Technology,2018,(06):506.[doi:10.13800/j.cnki.xakjdxxb.2018.0323]
[2]丁 华,王 剑,王 彬.基于灰关联分析和神经网络的煤与瓦斯突出预测[J].西安科技大学学报,2009,(02):136.
 DING Hua,WANG Jian,WANG Bin.Coal and gas outburst forecast based on ANN and grey correlation[J].Journal of Xi'an University of Science and Technology,2009,(06):136.
[3]高 宁,高彩云,吴良才.GPS高程迭加拟合模型的研究[J].西安科技大学学报,2009,(03):339.
 GAO Ning,GAO Cai-yun,WU Liang-cai.Research of combined model for GPS height[J].Journal of Xi'an University of Science and Technology,2009,(06):339.
[4]赵忠杰,田 梅.数据融合技术在公路隧道火灾探测中的应用[J].西安科技大学学报,2007,(03):435.
 ZHAO Zhong-jie,TIAN Mei.Application of data fusion technology to highway tunnels fire detection[J].Journal of Xi'an University of Science and Technology,2007,(06):435.

备注/Memo

备注/Memo:
收稿日期:2018-03-15 责任编辑:高 佳
基金项目::陕西省科技计划(2015KTCXSF-10-13); 咸阳市科技计划(2017K01-25-6)
通信作者:卫 晨(1983-),男,山西洪洞人,讲师,E-mail:weichen@xupt.edu.cn
更新日期/Last Update: 2018-11-15