基于动态图卷积Transformer的瓦斯浓度预测模型

打开文本图片集

中图分类号：TD712 文献标志码：A

Abstract：Accurate prediction of gas concentration is crucial for preventing gas disasters.The prediction accuracyis influenced by both the temporal variationpatternsofgasconcentrationand the spatiotemporal distribution characteristics of gas diffusion.Existing model-driven prediction methods struggle to handle longtermand large-scale gas concentration prediction tasks，whiledata-driven prediction methods do not consider the impact of dynamic spatial features，resulting in poor generalization performance.To capture the spatiotemporal dependencyof gasconcentration changesand improve the prediction accuracy，a Temporal-Dynamic Graph Convolutional Transformer with Multi-Scale Mechanism （TDMformer）was proposed to construct agas concentration prediction model.Based on the ITransformer framework，a temporal-variable attention mechanism was designed to model the temporal and variable featuressimultaneously.A dynamic graph convolutional network was integrated to describe the topologyof underground gas sensor networksand capture the spatial dependencyof gas concentration data.A multi-scale gated Tanh unit was introduced to enhance the multi-scale featureextractioncapability.The experimental results showed that，compared with Graph-WaveNet，GRU，Transformer， AGCRN，DSformer， STAEformer，and FourierGNN，the root mean square error of the TDMformer model decreased by 24.87% ， 26.37% ， 21.69% ， 19.57% ， 11.90% 10.84% and 9.20% ， respectively. The mean absolute error decreased by 17.09% 25.58% ， 26.89% ， 14.56% 11.10% 5.75% ，and 4.53% ，respectively.The coefficient of determination increased by 5.94% 6.51% ， 4.79% 4.12% 2.21% ， 2.08% ，and 1.76% ，respectively， verifying that this model had higher prediction accuracy and better data fiting performance.

Key words： gas concentration prediction; Transformer; ITransformer; dynamic graph convolutional network;temporal-variableattentionmechanism

0 引言

瓦斯突出和瓦斯爆炸是井下作业的高危隐患[1]，会导致生产系统瘫痪、资源损毁等重大经济损失，甚至威胁人员生命安全。（剩余16506字）