基于GCN-GRU的瓦斯浓度时空分布预测  

Spatiotemporal distribution prediction of gas concentration based on GCN-GRU

作　　者：秦嘉欣 葛淑伟 龙凤琪 张永茜 李雪 QIN Jiaxin;GE Shuwei;LONG Fengqi;ZHANG Yongqian;LI Xue(School of Mechanical Electronic and Information Engineering,China University of Mining and Technology-Beijing,Beijing 100083,China)

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《工矿自动化》2023年第5期82-89,111,共9页Journal Of Mine Automation

基　　金：国家自然科学基金重点资助项目(61936008)。

摘　　要：在煤矿井下复杂环境下,传统瓦斯浓度预测模型的预测精度较低,虽然通过引入各种优化算法对传统瓦斯浓度预测模型进行优化,提高了瓦斯浓度预测精度,但仅从时间维度进行建模,忽略了瓦斯浓度的空间特性,易导致重要先验知识丢失,影响预测效果。针对上述问题,提出一种基于图卷积神经网络(GCN)和门控循环单元(GRU)的瓦斯浓度时空分布预测模型。首先,对瓦斯浓度历史数据进行预处理,根据各采集节点间的空间距离,构建瓦斯浓度空间节点图,用于对节点间复杂的依赖关系进行建模。然后,在每个采样时间点,将瓦斯浓度和节点间的距离权重参数作为输入,获得瓦斯的空间节点图结构后,通过GCN进行空间特征自适应学习和图卷积运算,得到瓦斯浓度的空间特征,再将瓦斯浓度的空间特征信息转化为序列数据,输入到GRU。最后,GRU对时间序列下各时刻组成的瓦斯空间特征信息进行处理,通过基于序列到序列模型和自动编码器,生成模型预测结果。试验结果表明:(1) GCN-GRU模型能够较为准确地预测瓦斯浓度的总体变化趋势,预测结果与实际数据的拟合度优于历史平均(HA)模型和支持向量回归(SVR)模型。(2) GCN-GRU模型的均方根误差较HA模型、SVR模型、移动平均自回归(ARIMA)模型分别降低了0.5%,71.4%,37.9%,平均绝对误差分别降低了10.5%,82.4%,82.4%,准确率分别提高了0.06%,17.7%,13.8%,表明GCN-GRU模型具有较强的鲁棒性,且泛化性能较好。(3) GCN-GRU模型较HA模型、SVR模型、ARIMA模型更能关注到前序重要特征的影响。这主要是由于GRU的2个门关注了数据的时间特征,GRU在保留门控功能的基础上,减少训练参数,在一定程度上提高了模型训练效率,降低了训练时长。In the complex environment of coal mines,the prediction precision of traditional gas concentration prediction models is relatively low.Although the traditional gas concentration prediction model is optimized by introducing various optimization algorithms to improve the gas concentration prediction accuracy.But modeling only from the time dimension ignores the spatial features of gas concentration.This can easily lead to the loss of important prior knowledge and affect the prediction effect.In order to solve the above problems,a gas concentration spatiotemporal distribution prediction model based on graph convolutional networks(GCN)and gated recurrent unit(GRU)is proposed.Firstly,the historical data of gas concentration is preprocessed.A gas concentration spatial node graph is constructed based on the spatial distance between each collection node.The graph is used to model the complex dependency relationships between nodes.Secondly,at each sampling time point,the gas concentration and distance weight parameters between nodes are used as inputs to obtain the spatial node graph structure of gas.After that,GCN is used for spatial feature adaptive learning and graph convolution operation to obtain the spatial features of gas concentration.Then,the spatial feature information of gas concentration is transformed into sequence data and input to GRU.Finally,GRU processes the gas spatial feature information composed of each time under the time series.Through sequence-to-sequence based models and autoencoders,GRU generates model prediction results.The experimental results show the following points.①The GCN-GRU model can accurately predict the overall trend of gas concentration changes.The fit between the predicted results and actual data is better than the historical average(HA)model and support vector regression(SVR)model.②The root mean square error of GCN-GRU model is reduced by 0.5%,71.4%and 37.9%respectively compared with HA model,SVR model and autoregressive integrated moving average model(ARIMA)model.The average a

关 键 词：瓦斯浓度预测 瓦斯浓度时空特性 空间节点图 图卷积神经网络 门控循环单元 

分 类 号：TD712[矿业工程—矿井通风与安全]