|本期目录/Table of Contents|

[1]刘莹,杨超宇.基于多因素的LSTM瓦斯浓度预测模型*[J].中国安全生产科学技术,2022,18(1):108-113.[doi:10.11731/j.issn.1673-193x.2022.01.017]
　LIU Ying,YANG Chaoyu.LSTM gas concentration prediction model based on multiple factors[J].Journal of Safety Science and Technology,2022,18(1):108-113.[doi:10.11731/j.issn.1673-193x.2022.01.017]
点击复制

基于多因素的LSTM瓦斯浓度预测模型*

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

卷:
18
期数:
2022年1期
页码:
108-113
栏目:
职业安全卫生管理与技术
出版日期:
2022-01-31

文章信息/Info

Title:
LSTM gas concentration prediction model based on multiple factors
文章编号:
1673-193X(2022)-01-0108-06
作者:
刘莹; 杨超宇
（安徽理工大学 经济与管理学院，安徽 淮南 232001）
Author(s):
LIU Ying; YANG Chaoyu
(School of Economics and Management,Anhui University of Science and Technology,Huainan Anhui 232001,China)
关键词:
LSTM; 瓦斯浓度预测; 数据融合; 时间序列; 特征衍生
Keywords:
long short-term memory (LSTM);  gas concentration prediction;  data fusion;  time series;  feature derivation
分类号:
X936；TD712
DOI:
10.11731/j.issn.1673-193x.2022.01.017
文献标志码:
A
摘要:
为解决煤矿瓦斯浓度预测问题，提出基于多因素的LSTM瓦斯浓度预测模型。模型首先对煤矿多源监测数据进行数据融合、缺失值处理；其次通过特征衍生、有监督化、无量纲化，融合各环境因素特征和时序数据的时间性特征，且衍生出更多交叉项特征和高次项特征；然后利用经验法和逐步试错法确定隐藏层维度；最后进行模型训练和测试。研究结果表明：基于多因素的LSTM瓦斯浓度预测模型的RMSE仅为0.021，MAE为0.01，比单因素LSTM模型、RNN模型预测效果好。因此，基于多因素的LSTM瓦斯浓度预测模型可更精准地进行瓦斯浓度多步预测，促进煤矿安全生产。
Abstract:
In order to solve the problem of gas concentration prediction in coal mine,a LSTM gas concentration prediction model based on multiple factors was put forward.Firstly,the data fusion and missing value processing of multi-source monitoring data in coal mine were conducted.Secondly,through the feature derivation,supervision and dimensionless,the characteristics of various environmental factors and the temporal characteristics of time series data were fused,and more cross-term features and high-order features were derived.Thirdly,the empirical method and stepwise trial-and-error method were used to determine the hidden layer dimension.Finally,the model was trained and tested.The results showed that the RMSE of LSTM gas concentration prediction model based on multiple factors was only 0.021,and MAE was 0.01,so the prediction performance was better than that of single-factor LSTM model and RNN model.Therefore,the LSTM gas concentration prediction model based on multiple factors can more accurately predict the gas concentration in multiple steps and promote the work safety of coal mines.

参考文献/References:

［1］雷思友,刘洁,方信.煤与瓦斯突出影响因素综合评价研究——基于改进熵权法+灰色系统关联法的研究［J］.煤,2021,30(7):21-24,56. LEI Siyou,LIU Jie,FANG Xin.Comprehensive evaluation of influence factors of coal and gas outburst——based on the improved entropy weight method+grey system correlation method［J］.Coal,2021,30(7):21-24,56.
［2］司鹄,赵剑楠,胡千庭.大数据理论下的煤与瓦斯突出事故致因分析［J］.西安科技大学学报,2018,38(4):515-522,537. SI Hu,ZHAO Jiannan,HU Qianting.Analysis of causes of coal and gas outburst accidents based on big data theory［J］.Journal of Xi’an University of Science and Technology,2018,38(4):515-522,537.
［3］曹家琳,崔永国.煤矿瓦斯突出事故致因分类研究［J］.煤矿安全,2018,49(4):229-232. CAO Jialin,CUI Yongguo.Classified study on causal factors of coal mine gas outburst accidents［J］.Safety in Coal Mines,2018,49(4):229-232.
［4］蓝航,陈东科,毛德兵.我国煤矿深部开采现状及灾害防治分析［J］.煤炭科学技术,2016,44(1):39-46. LAN Hang,CHEN Dongke,MAO Debing.Current status of deep mining and disaster prevention in China［J］.Coal Science and Technology,2016,44(1):39-46.
［5］武风波,吕茜彤.基于嵌入式的井下环境监测系统设计［J］.现代电子技术,2019,42(13):42-46. WU Fengbo,LYU Qiantong.Design of downhole environmental monitoring system based on embedded technology［J］.Modern Electronics Technique,2019,42(13):42-46.
［6］吴奉亮,霍源,高佳南.基于随机森林回归的煤矿瓦斯涌出量预测方法［J］.工矿自动化,2021,47(8):102-107. WU Fengliang,HUO Yuan,GAO Jianan.Coal mine gas emission prediction method based on random forest regression［J］.Industry and Mine Automation,2021,47(8):102-107.
［7］林海飞,周捷,高帆,等.基于特征选择和机器学习融合的煤层瓦斯含量预测［J］.煤炭科学技术,2021,49(5):44-51. LIN Haifei,ZHOU Jie,GAO Fan,et al.Coal seam gas content prediction based on fusion of feature selection and machine learning［J］.Coal Science and Technology,2021,49(5):44-51.
［8］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. ZHENG Xiaoliang,LAI Wenhao,XUE Sheng.Application of MI and SVM in coal and gas outburst prediction［J］.China Safety Science Journal,2021,31(1):75-80.
［9］高望,张岩,高帅帅.基于BP神经网络的未采区瓦斯含量预测［J］.陕西煤炭,2020,39(1):77-80. GAO Wang,ZHANG Yan,GAO Shuaishuai.Prediction of gas content in unmined area based on BP neural network［J］.Shaanxi Coal,2020,39(1):77-80.
［10］许满贵,高帅帅,曹艳军,等.基于灰色理论-多元回归分析的瓦斯含量预测［J］.煤矿安全,2018,49(9):211-214. XU Mangui,GAO Shuaishuai,CA0 Yanjun,et al.Forecast of gas content based on gray theory and multiple regression analysis［J］.Safety in Coal Mines,2018,49(9):211-214.
［11］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.
［12］李超群,李宏伟.一种基于支持向量机和模型树的回归模型及其在采煤工作面瓦斯涌出量预测中的应用［J］.应用基础与工程科学学报,2011,19(3):370-378. LI Chaoqun,LI Hongwei.ASVM and model tree based regression model and its application in predicting the amount of gas emitted from coalface ［J］.Journal of Basic Science and Engineering,2011,19(3):370-378.
［13］刘鹏,魏卉子,景江波,等.基于增强CART回归算法的煤矿瓦斯涌出量预测技术［J］.煤炭科学技术,2019,47(11):116-122. LIU Peng,WEI Huizi,JING Jiangbo,et al.Predicting technology of gas emission quantity in coal mine based on enhanced CART regression algorithm ［J］.Coal Science and Technology,2019,47(11):116-122.
［14］刘晓悦,刘婉晴,郭强.基于云计算的煤矿瓦斯浓度短期预测［J］.控制工程,2018,25(8):1364-1369. LIU Xiaoyue,LIU Wanqing,GUO Qiang.Coal mine gas concentration short-term prediction based on cloud computing ［J］.Control Engineering of China,2018,25(8):1364-1369.
［15］张震,朱权洁,李青松,等.基于Keras长短时记忆网络的矿井瓦斯浓度预测研究［J］.安全与环境工程,2021,28(1):61-67,78. ZHANG Zhen,ZHU Quanjie,LI Qingsong,et al.Prediction of mine gas concentration in heading face based on Keras long short time memory network ［J］.Safety and Environmental Engineering,2021,28(1):61-67,78.

相似文献/References:

[1]刘超,雷晨,李树刚,等.基于CNN-GRU的瓦斯浓度预测模型及应用*[J].中国安全生产科学技术,2022,18(9):62.[doi:10.11731/j.issn.1673-193x.2022.09.009]
　LIU Chao,LEI Chen,LI Shugang,et al.Prediction model of gas concentration based on CNN-GRU and its application[J].Journal of Safety Science and Technology,2022,18(1):62.[doi:10.11731/j.issn.1673-193x.2022.09.009]
[2]谢谦,董立红,吴雪菲.基于多源数据融合的煤矿工作面瓦斯浓度预测*[J].中国安全生产科学技术,2022,18(11):71.[doi:10.11731/j.issn.1673-193x.2022.11.010]
　XIE Qian,DONG Lihong,WU Xuefei.Prediction of gas concentration in coal mining face based on multi-source data fusion[J].Journal of Safety Science and Technology,2022,18(1):71.[doi:10.11731/j.issn.1673-193x.2022.11.010]
[3]孟晓静,王玮丹,李为君,等.双参数驱动的高层宿舍火源信息反演预测研究*[J].中国安全生产科学技术,2025,21(5):157.[doi:10.11731/j.issn.1673-193x.2025.05.020]
　MENG Xiaojing,WANG Weidan,LI Weijun,et al.Research on inversion prediction of fire source information in high-rise dormitory driven by double parameters[J].Journal of Safety Science and Technology,2025,21(1):157.[doi:10.11731/j.issn.1673-193x.2025.05.020]

备注/Memo

备注/Memo:
收稿日期： 2021-09-10
* 基金项目： 国家自然科学基金项目（61873004）
作者简介： 刘莹，硕士研究生，主要研究方向为自然语言处理、数据挖掘。
更新日期/Last Update: 2022-02-19