煤矿安全2025，Vol.56Issue(12)：10-18,9.DOI:10.13347/j.cnki.mkaq.20251141
基于多智能体强化学习的煤矿智能瓦斯巡检机器人网络化控制研究
Networked control of intelligent gas inspection robots in coal mines based on multi-agent reinforcement learning
摘要
Abstract
To enhance the safety and real-time performance of underground gas inspection in coal mines and to overcome the low ef-ficiency and high risk associated with manual inspection,a networked intelligent control approach integrating perception and de-cision-making was developed.Relying on multi-agent reinforcement learning(MARL),the framework constructs an embedded dual-module system that combines object recognition with cooperative path planning.The perception module utilizes the lightweight YOLO-Float detection network,which is optimized through structural pruning and 8-bit quantization to balance computational effi-ciency and accuracy.Furthermore,by integrating multi-scale feature fusion and attention mechanisms,the model achieves high-pre-cision recognition of gas pipelines,valves,and dynamic obstacles.The decision-making layer introduced local optimal guidance,crossover mutation and information self-adaptive update mechanism based on the ant colony optimization algorithm,and formed an improved ant colony optimization(IACO)algorithm to complete the path planning.On the Gazebo three-dimensional mine simula-tion dataset,the constructed model was compared with the reference model.A 24-hour small-scale continuous inspection test was also conducted in the real mine environment.The test indicators covered detection accuracy,root mean square error(RMSE),path planning success rate,convergence generations,system failure rate,energy consumption,and data packet loss rate,etc.The simula-tion results show that after 50 iterations,the path fitness of the model reached 0.92,the root mean square error was 0.15,the detec-tion accuracy was 88.3%,the average accuracy mean was 90.1%,and the training time with 800 frames of data was 1.8 seconds,and the processing delay was 3.2 seconds.Compared with the traditional model,it was shortened by 28%and 20%respectively.In the actual mine tests,the detection accuracy remained at 87.9%,the comprehensive failure rate was 1.8%,the communication interrup-tion rate was 0.6%,the path planning failure rate was 0.7%,the average response delay was 2.8 seconds,the energy consumption was 14.6 Wh,and the data packet loss rate was 0.4%.Even under weak illumination and high humidity conditions,the detection accur-acy still remained above 85%,and the path planning success rate was around 95%.The research results show that this method has achieved high-precision and low-latency autonomous gas inspection in coal mines.关键词
煤矿智能化/多智能体/强化学习/目标识别/路径规划/瓦斯巡检机器人Key words
coal mine intelligentization/multi-agent/reinforcement learning/object recognition/path planning/gas inspection robot分类
矿业与冶金引用本文复制引用
CHEN Xiangyuan..基于多智能体强化学习的煤矿智能瓦斯巡检机器人网络化控制研究[J].煤矿安全,2025,56(12):10-18,9.基金项目
国家能源投资集团有限责任公司科技创新资助项目(GJNY-23-140) （GJNY-23-140）
