|本期目录/Table of Contents|

[1]彭然.基于深度Q网络的矿井通风智能决策算法研究*[J].中国安全生产科学技术,2026,22(5):76-83.[doi:10.11731/j.issn.1673-193x.2026.05.009]
　Peng Ran.Research on intelligent decision-making algorithm for mine ventilation based on deep Q-network[J].Journal of Safety Science and Technology,2026,22(5):76-83.[doi:10.11731/j.issn.1673-193x.2026.05.009]
点击复制

基于深度Q网络的矿井通风智能决策算法研究*

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

卷:
22
期数:
2026年5期
页码:
76-83
栏目:
安全工程技术
出版日期:
2026-05-30

文章信息/Info

Title:
Research on intelligent decision-making algorithm for mine ventilation based on deep Q-network
文章编号:
1673-193X(2026)-05-0076-08
作者:
彭然
（1.煤科通安（北京）智控科技有限公司，北京 100013；
2.煤炭科学技术研究院有限公司，北京 100013；
3.智能开采与岩层控制全国重点实验室，北京 100013）
Author(s):
Peng Ran
(1.Coal Branch Tongan (Beijing) Intelligent Control Technology Co.,Ltd.,Beijing 100013,China;
2.China Coal Research Institute,Beijing 100013,China;
3.State Key Laboratory Intelligent Coal Mining and Strata Control,Beijing 100013,China)
关键词:
矿井通风系统; 智能决策; 深度Q网络; 仿真实验; 调控方案
Keywords:
mine ventilation system;  intelligent decision making;  deep Q-network;  simulation experiment;  regulation scheme
分类号:
X936；TD72
DOI:
10.11731/j.issn.1673-193x.2026.05.009
文献标志码:
A
摘要:
为解决矿井通风系统高度复杂性与动态时变性，传统调控方法难以实现实时优化的问题，提出了1种基于深度Q网络（deep Q-network，DQN）的矿井通风智能决策算法，通过强化学习机制动态优化通风参数，以回风侧粉尘质量浓度、工作面粉尘质量浓度及死角瓦斯体积分数等多源监测数据作为状态输入，通过Q值迭代学习生成最优风筒参数调控方案。研究结果表明：训练后的DQN算法能有效适应井下环境变化，所提调控方案显著改善了通风系统性能，其中回风侧与工作面平均降尘率分别达7.54%与10.94%，死角瓦斯体积分数平均降低11.40%；该算法可实时响应环境波动，动态调整风筒参数，克服了传统方法灵活性不足的缺陷，验证了深度强化学习在矿井通风领域的应用潜力。研究结果可为通风系统智能化控制提供技术参考。
Abstract:
In order to address the high complexity and dynamic variability of the mine ventilation system,which make it difficult for traditional decision-making methods to achieve real-time optimization.This paper proposes an intelligent decision-making algorithm for mine ventilation based on the deep Q-network (DQN),which dynamically optimizes ventilation parameters through reinforcement learning.The algorithm takes key parameters such as dust concentration on the return side,dust concentration at the working face,and gas concentration in dead zones as state inputs,and generates an optimal regulation scheme for air duct parameters via Q-value iterative optimization.Research results demonstrate that the trained DQN algorithm can effectively adapt to changes in the underground environment,and the proposed regulation scheme significantly improves the performance of the ventilation system: the average dust reduction rates on the return side and the working face reach 7.54% and 10.94%,respectively,and the average reduction rate of gas concentration in dead zones is 11.40%.The algorithm can respond to environmental fluctuations in real time and dynamically adjust air duct parameters,thereby overcoming the inflexibility of traditional methods.The research results can provide technical references for the intelligent control of ventilation systems.

参考文献/References:

［1］卢新明,尹红,矿井通风智能化理论与技术［J］.煤炭学报,2020,45(6):2236-2247. Lu Xinming,Yin Hong.The inteligent theory and technology of mine ventilation［J］.Journal of China Coal Society,2020,45(6):2236-2247.
［2］Semin M A,Levin L Y.Stability of air flows in mine ventilation network［J］.Process Safety and Environmental Protection,2019,124:1135-1143.
［3］张庆华,姚亚虎,赵吉玉.我国矿井通风技术现状及智能化发展展望［J］.煤炭科学技术,2020,48(2):97-103. Zhang Qinghua,Yao Yahu,Zhao Jiyu.Current situation of mine ventilation technology in China and outlook of intelligent development［J］.Coal Science and Technology,2020,48(2):97-103.
［4］金智新,王宏伟,付翔.HCPS理论体系下新一代智能煤矿发展路径［J］.工矿自动化,2022,48(10):1-12. Jin Zhixin,Wang Hongwei,Fu Xiang.Development path of new generation intelligent coal mine under HCPS theory system［J］.Industrial and Mining Automation,2022,48(10):1-12.
［5］李江,陈开岩,林柏泉.遗传算法在矿井通风网络优化中的应用［J］.中国矿业大学学报,2007,36(6):789-793. Li Jiang,Chen Kaiyan,Lin Boquan.Application of genetic algorithm in mine ventilation network optimization［J］.Journal of China University of Mining and Technology,2007,36(6):789-793.
［6］Hu Yunan,Koroleva O,Imiroslav K.Nonlinear control of mine ventilation networks［J］.Systems & Control Letters,2003,49(4):239-254.
［7］Cross H.Analysis of flow in networks of conduits or conductors［J］.University of Illinois Bulletin,1936,286(1):42-47.
［8］Scott D,Hinsley F.Ventilation network theory［J］.Colliery Engineering,1951,28(326):159-166.
［9］钟德云,王李管,毕林,等.基于回路风量法的复杂矿井通风网络解算算法［J］.煤炭学报,2015,40(2):365-370. Zhong Deyun,Wang Liguan,Bi Lin,et al.A complex mine ventilation network solution algorithm based on loop airflow method［J］.Journal of China Coal Society,2015,40(2):365-370.
［10］孔令标,侯运炳.基于Arc/Info的矿井风网解算方法研究［J］.矿冶工程,2003(3):15-17. Kong Lingbiao,Hou Yunbing.Research on mine wind network solution method based on Arc/Info［J］.Mining and Metallurgical Engineering,2003(3):15-17.
［11］Wang Jinmiao,Xiao Jun,Xue Yan,et al.Optimization of arflow distribution in mine ventilation networks using the modified sooty tern optimization algorithm［J］.Mining,Metallurgy & Exploration,2024,41(1):239-257.
［12］吴新忠,韩正化,魏连江,等.矿井风流智能按需调控算法与关键技术［J］.中国矿业大学学报,2021,50(4):725-734. Wu Xinzhong,Han Zhenghua,Wei Lianjiang,et al.Intelligent on-demand adjustment algorithm and key technology of mine air flow［J］.Journal of China University of Mining and Technology,2021,50(4):725-734.
［13］贾进章,刘剑,倪景峰.通风系统可靠性稳定性及灵敏性数学模型［J］,辽宁工程技术大学学报(自然科学版),2003,22(6):725-727. Jla Jinzhang,Liu Jian,Ni Jingfeng.Mathematical models for reliability stability and sensitivity of ventilation system［J］.Journal of Liaoning Technical University (Natural Science),2003,22(6):725-727.
［14］Chatterjee A,Zhang Liun,Xia Xiaohua.Optimization of mine ventilation fan speeds according to ventilation on demand and time of use tariff［J］.Applied Energy,2015,146:65-73.
［15］Jia Peng,Jia Jinzhang,Song Lei,et al.Theory of RPOD adjustment of air volume for mine intelligent ventilation［J］.International Journal of Ventilation.2022,21(4):316-329.
［16］李源.南岭煤矿工作面智能化风量调控技术研究［J］.煤炭与化工,2025,48(3):106-109,118. Li Yuan.Research on intelligent air volume regulation and control technology of working face in Nanling coal mine［J］.Coal and Chemical Industry,2025,48(3):106-109,118.
［17］赵亮,邢思云,张德灿,等.对角式系统通风困难时期矿井风量调控技术［J］.科学技术创新,2025(8):42-47. Zhao Liang,Xing Siyun,Zhang Decan,et al.Techniques for regulating mine airflow during the difficult period of diagonal system ventilation［J］.Science and Technology Innovation,2025(8):42-47.
［18］张浪,雷爽,李伟,等.基于改进人工蜂群算法的矿井风量按需调控智能决策［J］.工矿自动化,2025,51(3):131-137. Zhang Lang,Lei Shuang,Li Wei,et al.Intelligent decision-making for on-demand regulation of mine airflow based on improved artificial bee colony algorithm［J］.Industrial and Mining Automation,2025,51(3):131-137.
［19］Kashnikov A V,Levin L Y.Fan and regulators fuzzy control in mine ventilation systems［C］.2019 XXII International Conference on Soft Computing and Measurements (SCM).IEEE,2019:85-88.
［20］钟德云,文历学,王李管.基于混合整数规划的风流两步骤调控优化方法［J］.黄金科学技术,2024,32(2):356-365. Zhong Deyun,Wen Lixue,Wang Liguan.A two-step regulation optimization method for wind flow based on mixed integer programming［J］.Gold Science and Technology,2024,32(2):356-365.

相似文献/References:

[1]章能胜,张黔生,谢贤平,等.三种确定矿井通风系统设计方案评价指标权重的方法比较[J].中国安全生产科学技术,2012,8(12):38.
　ZHANG Neng sheng,ZHANG Qian sheng,XIE Xian ping,et al.Comparative study on three methods for the evaluation index weight of design scheme on mine ventilation system[J].Journal of Safety Science and Technology,2012,8(5):38.
[2]韩艳杰,张志军,李亚俊.基于新型综合集成法的矿井通风系统安全评价[J].中国安全生产科学技术,2014,10(2):75.[doi:10.11731/j.issn.1673-193x.2014.02.013]
　HAN Yan jie,ZHANG Zhi jun,LI Ya jun.Evaluation of mine ventilation system safety based on new comprehensive integrated method[J].Journal of Safety Science and Technology,2014,10(5):75.[doi:10.11731/j.issn.1673-193x.2014.02.013]
[3]马恒,苗倩斐,韩宝华,等.矿井通风系统稳定性SD预测仿真分析[J].中国安全生产科学技术,2019,15(12):108.[doi:10.11731/j.issn.1673-193x.2019.12.018]
　MA Heng,MIAO Qianfei,HAN Baohua,et al.SD prediction and simulation analysis on stability of mine ventilation system[J].Journal of Safety Science and Technology,2019,15(5):108.[doi:10.11731/j.issn.1673-193x.2019.12.018]
[4]刘剑,刘丽,黄德,等.基于风量-风压复合特征的通风系统阻变型故障诊断[J].中国安全生产科学技术,2020,16(1):85.[doi:10.11731/j.issn.1673-193x.2020.01.014]
　LIU Jian,LIU Li,HUANG De,et al.Resistance variant fault diagnosis of ventilation system based on composite features of air volume and air pressure[J].Journal of Safety Science and Technology,2020,16(5):85.[doi:10.11731/j.issn.1673-193x.2020.01.014]
[5]程刚,陆卫东,陈志峰,等.基于FAHP-MODM的矿井通风系统可靠性综合评价[J].中国安全生产科学技术,2018,14(2):99.[doi:10.11731/j.issn.1673-193x.2018.02.016]
　CHENG Gang,LU Weidong,CHEN Zhifeng,et al.Comprehensive evaluation on reliability of ventilation system in mine based on FAHP-MODM[J].Journal of Safety Science and Technology,2018,14(5):99.[doi:10.11731/j.issn.1673-193x.2018.02.016]
[6]邵良杉,张佳琦,于保才,等.基于TF-熵权法的矿井通风系统可靠性可拓评价*[J].中国安全生产科学技术,2022,18(4):106.[doi:10.11731/j.issn.1673-193x.2022.04.015]
　SHAO Liangshan,ZHANG Jiaqi,YU Baocai,et al.Extension evaluation on reliability of mine ventilation system based on TF-entropy weight method[J].Journal of Safety Science and Technology,2022,18(5):106.[doi:10.11731/j.issn.1673-193x.2022.04.015]

备注/Memo

备注/Memo:
收稿日期： 2025-12-04；修回日期：2026-01-27
* 基金项目： 煤炭科学技术研究院有限公司科技发展基金项目（2025ZDI-06）
作者简介： 彭然，硕士，副研究员，主要研究方向为矿井通风与安全技术装备。
更新日期/Last Update: 2026-06-03