PDF下载

[1]杜学平,赵清华,秘琳,等.基于BP-ARIMA的中国月度LNG出厂价格预测模型[J].油气储运,2024,43(10):1-12.
　DU Xueping,ZHAO Qinghua,MI Lin,et al.Forecasting Model of Chinas Monthly LNG Ex-factory Prices based on BP-ARIMA[J].Oil & Gas Storage and Transportation,2024,43(10):1-12.

点击复制

基于BP-ARIMA的中国月度LNG出厂价格预测模型

《油气储运》[ISSN:1000-8241/CN:13-1093/TE] 卷: 43 期数: 2024年10期页码: 1-12 栏目: 出版日期: 2024-10-25

Title:: Forecasting Model of China's Monthly LNG Ex-factory Prices based on BP-ARIMA

作者:: 杜学平; 赵清华; 秘琳; 郎智凯; 柳梦琳; 吴江涛

Author(s):: DU Xueping; ZHAO Qinghua; MI Lin; LANG Zhikai; LIU Menglin; WU Jiangtao

关键词:: LNG; 变权重组合预测模型; BP神经网络; ARIMA模型; 价格预测

Keywords:: Liquefied natural gas; Variable weight combination prediction model; BP neural network; ARIMA model; Price forecasting

分类号:: TK01+1

文献标志码:: A

摘要:: 【目的】中国作为全球最大的天然气进口国，LNG在天然气供给中扮演着关键角色。然而中国LNG出厂价格的变化呈现较强的不确定性和波动性，准确预测中国LNG出厂价格的变化趋势，对LNG产业链布局优化、提高天然气供应链的经济性具有重要现实意义。【方法】研究收集并整理了中国LNG出厂价格的历史数据，并采用灰色关联分析确定了影响价格变动的关键因素。在此基础上，分别构建BP神经网络预测模型与ARIMA时间序列预测模型。根据变权重理论，将两种单一预测模型进行加权组合，建立新的变权重BP-ARIMA组合预测模型。以中国实际LNG出厂价格数据对不同预测模型进行案例验证分析。【结果】与传统的BP神经网络模型和ARIMA模型相比，变权重BP-ARIMA组合模型结合了两种单一模型的优势，通过动态调整两种模型的权重比例，显著提高了LNG出厂价格预测的准确性。其平均绝对误差MAE、平均绝对百分比误差MAPE以及均方根误差RMSE分别为188.7元/t、4.1%、280.5元/t，相较于BP神经网络模型、ARIMA模型以及等权重组合模型，MAE分别降低了65.85%、44.2%、37.5%，RMSE降低了63.6%、38.2%、29.8%，MAPE降低了63.7%、42.3%、36.9%。【结论】研究所提出的变权重BP-ARIMA组合预测模型为中国LNG出厂价格预测难题提供了有效解决方案，有助于促进LNG市场有序发展并为天然气供应链管理提供决策支持。

Abstract:: [Objective]As the world's largest natural gas importer, LNG (liquefied natural gas) plays a critical role in China's natural gas supply. However, the changes in China's LNG ex-factory prices exhibit significant uncertainty and volatility. Accurately predicting the trend of changes in China's LNG ex-factory prices has important practical significance for optimizing the LNG industry chain layout and improving the economic efficiency of the natural gas supply chain. 【Methods】This study collected and organized the historical data of China's LNG ex-factory prices and used grey relational analysis to identify the key factors influencing price changes. Based on this, BP neural network prediction model and ARIMA time series prediction model were respectively established. According to the varying-weight theory, the two individual prediction models were combined with weighted aggregation to establish a new varying-weight BP-ARIMA combined prediction model. The case verification analysis of different prediction models was conducted based on the actual LNG ex-factory price data in China. [Results] The prediction results show that compared to the traditional BP neural network model and ARIMA model, the varying-weight BP-ARIMA combined model combines the advantages of the two individual models, and by dynamically adjusting the weight ratio of the two models, it significantly improves the accuracy of LNG ex-factory price forecasting. Its mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) are 188.7 yuan/ton, 4.1%, and 280.5 yuan/ton, respectively, which are 65.85%, 44.2%, and 37.5% lower in MAE, 63.6%, 38.2%, and 29.8% lower in RMSE, and 63.7%, 42.3%, and 36.9% lower in MAPE compared to the BP neural network model, ARIMA model, and equal-weight combination model, respectively. [Conclusion] The varying-weight BP-ARIMA combined prediction model proposed in this study provides an effective solution to the problem of forecasting China's LNG ex-factory prices, which is helpful for promoting the orderly development of the LNG market and providing decision support for natural gas supply chain management.

相似文献/References:

[1]胡德新.天然气的地下岩洞储存[J].油气储运,2010,29(3):165.[doi:10.6047/j.issn.1000-8241.2010.03.002]
　Hu Dexin.Underground Cavern Storage of Natural Gas[J].Oil & Gas Storage and Transportation,2010,29(10):165.[doi:10.6047/j.issn.1000-8241.2010.03.002]
[2]朱鸿梅,孙恒,刘宏伟.大型 LNG 储罐角部绝热结构的温度场[J].油气储运,2011,30(01):37.[doi:10.6047/j.issn.1000-8241.2011.01.010]
　Zhu Hongmei,Sun Heng,Liu Hongwei.Temperature field on corner adiabatic structure of large-scale LNG storage tank[J].Oil & Gas Storage and Transportation,2011,30(10):37.[doi:10.6047/j.issn.1000-8241.2011.01.010]
[3]王彦,信鹏,高萃仙,等.LNG接收站蒸发气的发生与气量计算[J].油气储运,2010,29(5):363.[doi:10.6047/j.issn.1000-8241.2010.05.013]
　Wang Van,Xin Peng,Gao Cuixian.Generation of Vapour and Vapour Volurne Calculation for LNG Receiving Station[J].Oil & Gas Storage and Transportation,2010,29(10):363.[doi:10.6047/j.issn.1000-8241.2010.05.013]
[4]王海蓉梁栋.LNG 分层翻滚事故可预测性与盐水模化实验[J].油气储运,2012,31(4):246.[doi:10.6047/j.issn.1000-8241.2012.04.002]
　Wang Hairong and Liang Dong.Predictability of LNG stratification rollover and salt water modeling experiment[J].Oil & Gas Storage and Transportation,2012,31(10):246.[doi:10.6047/j.issn.1000-8241.2012.04.002]
[5]孙青峰,赵德贵.LNG接收站储罐配置[J].油气储运,2009,28(3):17.[doi:10.6047/j.issn.1000-8241.2009.03.006]
　SUN Qingfeng,ZHAO Degui.Configuration of Tanks in LNG Terminal Stations[J].Oil & Gas Storage and Transportation,2009,28(10):17.[doi:10.6047/j.issn.1000-8241.2009.03.006]
[6]邵铁民.LNG冷能及其利用[J].油气储运,2007,26(11):41.[doi:10.6047/j.issn.1000-8241.2007.11.012]
　SHAO Tiemin.Cold Energy of LNG and its Comprehensive Utilization[J].Oil & Gas Storage and Transportation,2007,26(10):41.[doi:10.6047/j.issn.1000-8241.2007.11.012]
[7]赵保才,李涛.LNG静态测量计算[J].油气储运,2006,25(8):36.[doi:10.6047/j.issn.1000-8241.2006.08.010]
　ZHAO Baocai,LI Tao.Static Measnrement and Calculation of LNG[J].Oil & Gas Storage and Transportation,2006,25(10):36.[doi:10.6047/j.issn.1000-8241.2006.08.010]
[8]李安,李小瑜,邵勇,等.某LNG站管网与管径的优化计算[J].油气储运,2005,24(11):19.[doi:10.6047/j.issn.1000-8241.2005.11.006]
　LI An,LI Xiaoyu.Optimal Calculation on Pipeline Network and Pipe Diameter for Some LNG Statoin[J].Oil & Gas Storage and Transportation,2005,24(10):19.[doi:10.6047/j.issn.1000-8241.2005.11.006]
[9]付愉庆,刘飞飞,肖丁,等.LNG气化装置在城市燃气系统中的应用[J].油气储运,2009,28(9):58.[doi:10.6047/j.issn.1000-8241.2009.09.019]
　FU Yuqing,LIU Feifei.Application of LNG Gasification Unit in City Gas System[J].Oil & Gas Storage and Transportation,2009,28(10):58.[doi:10.6047/j.issn.1000-8241.2009.09.019]
[10]孟庆萍.海上盐穴LNG接收终端[J].油气储运,2009,28(6):38.[doi:10.6047/j.issn.1000-8241.2009.06.011]
　MENG Qingping.Offshore Salt-Cavern-based LNG Receiving Terminals[J].Oil & Gas Storage and Transportation,2009,28(10):38.[doi:10.6047/j.issn.1000-8241.2009.06.011]

更新日期/Last Update: 2024-08-12