img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2024, Vol. 32 ›› Issue (3): 548-558.doi: 10.11872/j.issn.1005-2518.2024.03.118

• 采选技术与矿山管理 • 上一篇    

基于改进灰色模型的钢铁工业生产能耗预测研究

邓高(),李琪   

  1. 湖南钢铁集团有限公司,湖南 长沙 410004
  • 收稿日期:2023-08-21 修回日期:2024-04-19 出版日期:2024-06-30 发布日期:2024-07-05
  • 作者简介:邓高(1975-),男,湖南宁乡人,正高级经济师,从事资源与环境经济学、企业管理等工作。1652102421@qq.com

Research on Energy Consumption Prediction of Steel Industry Production Based on Improved Grey Models

Gao DENG(),Qi LI   

  1. Hunan Iron and Steel Group Co. ,Ltd. ,Changsha 410004,Hunan,China
  • Received:2023-08-21 Revised:2024-04-19 Online:2024-06-30 Published:2024-07-05

摘要:

在双碳目标背景下,开展钢铁工业生产能耗预测研究对于钢铁工业降低生产能耗和提升效益具有重要作用。为科学预测钢铁工业生产能耗,基于2010—2022年钢铁能耗数据,通过建立DNGM(1,1)、IDGM(1,1)和DDGM(1,1)3种改进的灰色预测模型,对吨钢综合能耗和吨钢可比能耗进行数据预测和误差对比分析,选出最优模型,得到2023—2025年吨钢综合能耗和吨钢可比能耗预测结果。研究表明:灰色预测模型在钢铁能耗预测中具有可行性和适应性;DNGM(1,1)模型在钢铁工业生产能耗预测中整体模拟性能最优;2023—2025年吨钢综合能耗和吨钢可比能耗将持续下降。基于研究结果,建议我国钢铁行业进一步优化生产工艺和技术,改善能源结构,并加大对节能减排技术研发的投资,以达到节能降耗的效果,促进节能减碳目标的早日实现。

关键词: 钢铁工业, 吨钢综合能耗, 吨钢可比能耗, 灰色预测模型, 改进灰色模型

Abstract:

Under the background of double carbon target,the research on energy consumption prediction of steel industry plays an important role in reducing production efficiency and improving efficiency of steel industry.In order to scientifically predict the energy consumption of steel industry production,based on the data of iron and steel energy consumption from 2010 to 2022,three improved grey prediction models of DNGM(1,1),IDGM (1,1) and DDGM(1,1) were established to predict the comprehensive energy consumption per ton of steel and the comparable energy consumption per ton of steel.The data prediction and error comparison analysis were carried out to select the optimal model and obtain the prediction results from 2023 to 2025.The results show that the grey prediction model is feasible and adaptable in the prediction of steel energy consumption.The DNGM(1,1) model has the best overall simulation performance in the prediction of energy consumption in steel industry production.The comprehensive energy consumption per ton of steel and the comparable energy consumption per ton of steel will continue to decline from 2023 to 2025.

Key words: steel industry, comprehensive energy consumption per ton steel, comparable energy consumption per ton steel, grey prediction model, improved grey model

中图分类号: 

  • TF4

图1

2010—2022年我国重点钢铁企业吨钢综合能耗及其年增长率"

图2

2010—2022年我国重点钢铁企业吨钢可比能耗及其年增长率"

表1

DNGM(1,1)模型参数和参数估计值"

数据类型模型参数参数估计值
αβγa?b?c?
吨钢综合能耗0.9929-0.7623605.77210.0071-0.7650608.3231
吨钢可比能耗1.0099-22.8295557.9509-0.0098-11.3867560.9010

表2

IDGM(1,1)模型参数值"

数据类型β1β2Cy
吨钢综合能耗0.9207-5.6969-5.6176
吨钢可比能耗0.9889-5.5087-5.4645

表3

DDGM(1,1)模型参数值"

数据类型β1β2AB
吨钢综合能耗0.946827.019489.6520508.3480
吨钢可比能耗0.9960-2.99461 299.6968-749.6968

表4

吨钢综合能耗灰色预测结果"

年份吨钢综合能耗DNGM(1,1)IDGM(1,1)DDGM(1,1)
模拟数据/预测数据残差相对误差/%模拟数据/预测数据残差相对误差/%模拟数据/预测数据残差相对误差/%
平均相对模拟误差/%0.70411.36771.1043
2010598598.000.000.00598.000.000.00598.000.000.00
2011597600.753.750.63597.000.000.00593.23-3.770.63
2012598595.71-2.290.38586.21-11.791.97588.72-9.281.55
2013590590.700.700.12581.45-8.551.45584.45-5.550.94
2014585585.730.730.13577.06-7.941.36580.41-4.590.79
2015580580.800.800.14573.03-6.971.20576.58-3.420.59
2016583575.90-7.101.22569.31-13.692.35572.95-10.051.72
2017576571.03-4.970.86565.89-10.111.76569.52-6.481.13
2018569566.20-2.800.49562.74-6.261.10566.26-2.740.48
2019553561.418.411.52559.846.841.24563.1910.191.84
2020549556.647.641.39557.178.171.49560.2711.272.05
2021550551.921.920.35554.714.710.86557.517.511.37
2022554547.22-6.781.22552.44-1.5560.28554.900.900.16
2023-542.56--550.36--552.42--
2024-537.93--548.44--550.08--
2025-533.34--546.67--547.86--

图3

吨钢综合能耗预测性能比较"

表5

吨钢可比能耗灰色预测结果"

年份吨钢可比能耗DNGM(1,1)IDGM(1,1)DDGM(1,1)
模拟数据/预测数据残差相对误差/%模拟数据/预测数据残差相对误差/%模拟数据/预测数据残差相对误差/%
平均相对模拟误差/%0.73691.30761.0187
2010550550.000.000.00550.000.000.00550.000.000.00
2011546551.935.931.09546.000.000.00544.81-1.190.22
2012545545.940.940.17535.13-9.871.81539.64-5.360.98
2013543539.88-3.120.58529.79-13.212.43534.49-8.511.57
2014539533.76-5.240.97524.50-14.502.69529.36-9.641.79
2015532527.58-4.420.83519.28-12.722.39524.25-7.751.46
2016525521.34-3.660.70514.11-10.892.08519.16-5.841.11
2017513515.042.040.40509.00-4.010.78514.091.090.21
2018505508.683.680.73503.94-1.060.21509.044.040.80
2019497502.265.261.06498.941.940.39504.027.021.41
2020493495.772.770.56494.001.000.20499.016.011.22
2021487489.222.220.46489.112.110.43494.027.021.44
2022489482.60-6.401.31484.27-4.7270.97489.050.050.01
2023-475.92--479.49--484.10--
2024-469.17--474.76--479.18--
2025-462.35--470.09--474.27--

图4

吨钢可比能耗预测性能比较"

Chao Yinkang, Gong Lixiong, Huang Xiao,et al,2023.Power consumption prediction and application of GM(1,1)-MEA-BP combined model[J].Journal of Chongqing University of Technology(Natural Science),37(7):306-314.
Cheng Guang, Li Lingyun, Ding Yi,et al,2014.Influencing factors of energy of consumption for iron steel enterprise systems[J].Iron and Steel,49(4):86-89.
Deng Gao, Yang Shan,2017.Analysis of mineral resources utilization based on grey cluster and grey prediction combined model[J].Gold Science and Technology,25(5):85-92.
Deng Junlong,1984.The diferential grey model(GM) and its implement in long period forecasting of grain[J].Discovery of Nature,(3):37-43.
Duan H M, Wang D, Pang X Y,et al,2020.A novel forecasting approach based on multi-kernel nonlinear multivariable grey model:A case report[J].Journal of Cleaner Production,260:120929.
Fan Zhongzhou, Zhao Yi, Zhou Ning,et al,2020.Integrated model for forecasting waterway traffic accidents based on the grey-BP neural network[J].Journal of Safety and Environment,20(8):857-861.
Feng Zhengyuan,1992.Direct grey model[J].Acta Mathematicae Applicatae Sinica,15(3):345-354.
Guo S D, Jing Y Q, Li B J,2022.Matrix form of interval multivariable gray model and its application[J].Grey Systems:Theory and Application,12(2):318-338.
Guo Xiaojun, Liu Sifeng, Fang Zhigeng,2014.Discrete DDGM prediction model of development belt based on the standard interval grey number[J].Mathematics in Practice and Theory,44(6):19-25.
He Chengxiang, Zeng Bo, Yang Lebin,2021.Prediction comparative analysis of PM2.5 in Chongqing based on parameter combination optimization of grey models[J].Journal of Systems Science and Mathematical Sciences,41(10):2855-2867.
He Kun, Wang Li,2021.Development and status of production energy consumption of China’s iron and steel industry[J].China Metallurgy,31(9):26-35.
Intharathirat R, Salam P A, Kumar S,et al,2015.Forecasting of municipal solid waste quantity in a developing country using multivariate grey models[J].Waste Management,39:3-14.
Lin B Q, Wang X L,2015.Carbon emissions from energy intensive industry in China:Evidence from the iron & steel industry[J].Renewable and Sustainable Energy Reviews,47:746-754.
Liu C, Lao T F, Wu W Z,et al,2022.An optimized nonlinear grey Bernoulli prediction model and its application in natural gas production[J].Expert Systems with Applications,194:116448.
Liu Qiang, Yan Xiu, Lu Yu,et al,2022.A grey relation projection-random forest prediction model of energy consumption for electric buses considering driving style[J].Journal of Transport Information and Safety,40(5):129-138.
Ma Hongyan, Cui Jie, Wang Yu,2019.Parameter properties of DDGM(1,1) model under scalar multiplication transformation of modeling sequence[J].Statistics and Decision,35(7):60-62.
Tong Mingyu, Zhou Xiaohua, Zeng Bo,2015.Expand of NGM(1,1) model based on the direct estimation method[J].Control and Decision,30(10):1841-1846.
Wang Jiangrong, Liu Shuo, Jin Cuncheng,2020.Application of grey G(1,1) model based on variable weight buffer operator in metro energy consumption prediction[J].Mathematics in Practice and Theory,50(7):90-96.
Wang Q, Li S Y, Li R R,et al,2018.Forecasting U.S. shale gas monthly production using a hybrid ARIMA and metabolic nonlinear grey model[J].Energy,160:378-387.
Wang Weixing,2017.The status of energy consumption of China and analysis of energy saving potential in iron and steel industry[J].China Steel Focus,(8):50-58.
Wang Xinpu, Zhou Xiangling, Xing Jie,et al,2016.A prediction of PV output power based on the combination of improved grey propagation neural network[J].Power System Protection and Control,44(18):81-87.
Wang Z X, Hipel K W, Wang Q,et al,2011.An optimized NGBM(1,1) model for forecasting the qualified discharge rate of industrial wastewater in China[J].Applied Mathematical Modelling,35(12):5524-5532.
World Steel Association,2023.World Steel in Figures 2023[OB/OL]..
Xie N M,2022.A summary of grey forecasting models[J].Grey Systems:Theory and Application,12(4):703-722.
Xie Naiming, Liu Sifeng,2005.Discrete GM(1,1) and mechanism of grey forecasting model[J].Systems Engineering-Theory & Practice,(1):93-99.
Xiong P P, Zou X, Yang Y J,2021.The nonlinear time lag multivariable grey prediction model based on interval grey numbers and its application[J].Natural Hazards,107(3):2517-2531.
Xu Hailun, Pan Guoyou, Shao Yuanjing,et al,2017.Analysis of energy consumption evaluation indication for iron and steel production[J].Energy for Metallurgical Industry,36(2):3-7,56.
Xu Lisong, Zhang Qi,2021.Analysis on energy consumption and CO2 emission trend of China’s iron and steel industry in key regions[J].China Metallurgy,31(9):36-45.
Yang Hualong, Liu Jinxia, Zheng Bin,2011.Improvement and application of grey prediction GM(1,1) model[J].Mathematics in Practice and Theory,41(23):39-46.
Zeng B, Duan H M, Zhou Y F,2019.A new multivariable grey prediction model with structure compatibility[J]Applied Mathematical Modelling,75:385-397.
Zeng B, Li H, Ma X,et al,2020.A novel multi-variable grey forecasting model and its application in forecasting the grain production in China[J].Computers & Industrial Engineering,150:106915.
Zeng Bo, Liu Sifeng,2010.Analysis of indirect DGM(1,1) model of non-homogeneous exponential incremental sequences[J].Journal of Statistics and Information,25(8):30-33.
Zeng Bo, Liu Sifeng,2012.Prediction model of stochastic oscillation sequence based on amplitude compression[J].Systems Engineering-Theory & Practice,32(11):2493-2497.
Zeng Bo, Liu Sifeng, Qu Xuexin,2017.Research on a grey common prediction modeling with strong compatibility and its properties[J].Chinese Journal of Management Science,25(5):150-156.
Zhang Chao,2023.Game Theory-based Research on Energy Conservation and Carbon Reduction Management Decisions in the Steel Industry[D].Beijing:University of Science and Technology.
Zhang F Y, Zhou Y D, Sun W Q,et al,2018.CO2 capture from reheating furnace based on the sensible heat of continuous casting slabs[J].International Journal of Energy Research,42(6):2273-2283.
Zhang Q, Wang Y J, Zhang W,et al,2019.Energy and resource conservation and air pollution abatement in China’s iron and steel industry[J].Resources Conservation and Recycling,147:67-84.
Zhou Zhiyong, Xiao Wei, Chen Jianhong,et al,2018.Prediction model of mine ecological environment based on PCA and GM(1,1) [J].Gold Science and Technology,26(3):372-378.
钞寅康,龚立雄,黄霄,等,2023.GM(1,1)-MEA-BP组合模型电能消耗预测及应用[J].重庆理工大学学报(自然科学),37(7):306-314.
陈光,李玲云,丁毅,等,2014.钢铁企业系统能耗影响因素分析[J].钢铁,49(4):86-89.
邓高,杨珊,2017.基于灰色聚类与灰色预测组合模型的矿产资源利用情况分析[J].黄金科学技术,25(5):85-92.
邓聚龙,1984.灰色动态模型(GM)及在粮食长期预测中的应用[J].大自然探索,(3):37-43.
范中洲,赵羿,周宁,等,2020.基于灰色BP神经网络组合模型的水上交通事故数预测[J].安全与环境学报,20(3):857-861.
冯正元,1992.直接灰色模型[J].应用数学学报,15(3):345-354.
郭晓君,刘思峰,方志耕,2014.基于标准区间灰数的发展带离散DDGM预测模型[J].数学的实践与认识,44(6):19-25.
何承香,曾波,杨乐彬,2021.基于灰色参数组合优化模型的重庆PM2.5浓度预测与对比分析[J].系统科学与数学,41(10):2855-2867.
何坤,王立,2021.中国钢铁工业生产能耗的发展与现状[J].中国冶金,31(9):26-35.
刘强,严修,鲁誉,等,2022.考虑驾驶风格的电动公交车能耗灰色关联投影-随机森林预测模型[J].交通信息与安全,40(5):129-138.
马红燕,崔杰,王雨,2019.建模序列数乘变换下的DDGM(1,1)模型参数特性[J].统计与决策,35(7):60-62.
童明余,周孝华,曾波,2015.基于直接估计法的NGM(1,1)模型拓展[J].控制与决策,30(10):1841-1846.
王江荣,刘硕,靳存程,2020.基于变权缓冲算子的灰色G(1,1)模型在地铁能耗预测中的应用[J].数学的实践与认识,50(7):90-96.
王维兴,2017.我国钢铁工业能耗现状与节能潜力分析[J].冶金管理,(8):50-58.
王新普,周想凌,邢杰,等,2016.一种基于改进灰色BP神经网络组合的光伏出力预测方法[J].电力系统保护与控制,44(18):81-87.
谢乃明,刘思峰,2005.离散GM(1,1)模型与灰色预测模型建模机理[J].系统工程理论与实践,(1):93-99.
徐海伦,潘国友,邵远敬,等,2017.钢铁生产能耗评估指标分析[J].冶金能源,36(2):3-7,56.
许立松,张琦,2021.中国重点区域钢铁产业能耗和CO2排放趋势分析[J].中国冶金,31(9):36-45.
杨华龙,刘金霞,郑斌,2011.灰色预测GM(1,1)模型的改进及应用[J].数学的实践与认识,41(23):39-46.
曾波,刘思峰,2010.近似非齐次指数增长序列的间接DGM(1,1)模型分析[J].统计与信息论坛,25(8):30-33.
曾波,刘思峰,2012.基于振幅压缩的随机振荡序列预测模型[J].系统工程理论与实践,32(11):2493-2497.
曾波,刘思峰,曲学鑫,2017.一种强兼容性的灰色通用预测模型及其性质研究[J].中国管理科学,25(5):150-156.
张朝,2023.基于博弈论的钢铁行业节能减碳管理决策研究[D].北京:北京科技大学.
周智勇,肖玮,陈建宏,等,2018.基于PCA和GM(1,1)的矿山生态环境预测模型[J].黄金科学技术,26(3):372-378.
[1] 周智勇, 肖玮, 陈建宏, 李欢. 基于PCA和GM(1,1)的矿山生态环境预测模型[J]. 黄金科学技术, 2018, 26(3): 372-378.
[2] 邓高,杨珊 . 基于灰色聚类与灰色预测组合模型的矿产资源利用情况分析[J]. 黄金科学技术, 2017, 25(5): 85-92.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 杨彦, 黄增保, 郭小刚, 许延龙, 颜华. 北祁连榆树沟山金矿区花岗闪长斑岩脉锆石U-Pb年龄、地球化学特征及其地质意义[J]. 黄金科学技术, 2024, 32(3): 387 -399 .
[2] 毕林,崔君*,林格,谢伟. 矿井火灾最优逃生路径优化数学模型的构建与实现[J]. 黄金科学技术, 2017, 25(2): 104 -109 .
[3] 李炎, 王建国, 魏生云, 李国璋, 胡建, 王志男. 西藏德新铅多金属矿床地球物理与地球化学综合找矿研究[J]. 黄金科学技术, 2024, 32(3): 400 -415 .
[4] 李启月, 肖宇航, 魏快快, 徐恒阳. 露天边坡体爆破振动特性研究[J]. 黄金科学技术, 2024, 32(3): 491 -500 .
[5] 李波, 温晨, 史秀志. 高应力扇形中深孔采场边帮控制爆破参数优化[J]. 黄金科学技术, 2024, 32(3): 511 -522 .
[6] 李祥龙, 余林, 黄原明, 陈浩, 赵艳伟. 基于VMD-HHT的井下预裂爆破振动效应分析[J]. 黄金科学技术, 2024, 32(3): 501 -510 .
[7] 胡松涛, 朱庚杰, 张军童, 徐世群, 寇云鹏. 胶东地区黄金矿山细尾砂胶结充填应用研究[J]. 黄金科学技术, 2024, 32(3): 425 -436 .
[8] 张涛, 李德贤, 张鹏强, 赵国亮, 何宇, 牛猛, 俞军真. 镍渣—全尾砂混合骨料配比试验研究[J]. 黄金科学技术, 2024, 32(3): 437 -444 .
[9] 虞云林, 侯克鹏, 杨八九, 程涌, 卢泰宏, 张楠楠. 云锡高峰山矿段矿柱回采方案研究[J]. 黄金科学技术, 2024, 32(3): 445 -457 .
[10] 张玉, 刘晓敏, 石怡安, 陈铁林, 王展魁, 陈文海, 孙加奇, 安平生. 动静复合拉拔作用下锚杆结构的破坏机制研究[J]. 黄金科学技术, 2024, 32(3): 481 -490 .