EMD-Attention-GRU天然气管网流量组合预测模型  

Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU

作　　者：门嘉铖 樊玉光[1] 高琳[1] 林红先 张科 MEN Jiacheng;FAN Yuguang;GAO Lin;LIN Hongxian;ZHANG Ke(Mechanical Engineering College,Xi'an Shiyou University;School of Materials Science and Engineering,Xi'an Shiyou University;Shaanxi Provincial Natural Gas Co.Ltd.)

机构地区：[1]西安石油大学机械工程学院 [2]西安石油大学材料科学与工程学院 [3]陕西省天然气股份有限公司

出　　处：《油气储运》2023年第10期1193-1200,共8页Oil & Gas Storage and Transportation

摘　　要：为了解决传统的时间序列预测方法在天然气管网流量预测中存在的不足,提出了一种基于经验模态分解(Empirical Mode Decomposition,EMD)、注意力机制(Attention)及门控循环单元(Gated Recurrent Unit,GRU)的组合模型。该模型利用EMD得到的原始天然气管网流量时间序列分量代替原始天然气管网流量数据,再将得到的本征模态函数分量输入GRU神经网络,采用在网络中集成的注意力机制计算不同时刻的注意力概率权重,最后在网络中学习并预测天然气管网流量时间序列。某天然气管网实例验证结果表明:EMD-AttentionGRU组合模型在预测天然气管网流量方面表现出良好的性能,能够捕捉到复杂的非线性关系,相比单一GRU模型、Attention-GRU模型,其预测结果的平均绝对百分比误差指标分别降低6.29%、5.17%。与传统时间序列预测方法相比,EMD-Attention-GRU组合模型能够更好应对天然气管网流量的复杂性及动态特征,具有推广应用价值。In order to overcome the deficiency of the traditional time series prediction method in flow prediction of natural gas pipeline networks,a combined prediction model based on Empirical Mode Decomposition(EMD),Attention and Gated Recurrent Unit(GRU)was proposed.Specifically,the model is to substitute the raw flow data of the natural gas pipeline network with its time series component obtained through Empirical Mode Decomposition(EMD),input the intrinsic mode function component obtained into the GRU neural network,calculate the attention probability weight at different times with the attention integrated into the network,and finally learn in the network and predict the time series of flow in the natural gas pipeline network.The verification results in a natural gas pipeline network show that:the EMD-Attention-GRU combined model demonstrates remarkable performance in flow prediction of natural gas pipeline network,capable of capturing the complex non-linear relationships.Besides,the average absolute percentage error of prediction by the combined model outperforms the single GRU and Attention-GRU models by 6.29%and 5.17%,respectively.Thus,it is indicated that the EMDAttention-GRU combined model could better address the complexities and dynamic features of flow in natural gas pipeline networks than the conventional time-series prediction methods,with values for promotion and application.

关 键 词：天然气管网 流量预测 经验模态分解(EMD) 注意力机制 门控循环单元(GRU) 

分 类 号：TE08[石油与天然气工程]