基于函數型數字孿生模型的轉爐煉鋼終點碳控制技術

徐鋼; 黎敏; 徐金梧; 賈春輝; 陳兆富

doi:10.13374/j.issn2095-9389.2019.04.013

基于函數型數字孿生模型的轉爐煉鋼終點碳控制技術

doi: 10.13374/j.issn2095-9389.2019.04.013

徐鋼^{1, 2},
黎敏^2, ,,
徐金梧²,
賈春輝³,
陳兆富³

1.
北京科技大學計算機與通訊工程學院，北京 100083
2.
鋼鐵共性技術協同創新中心，北京 100083
3.
鞍鋼股份鲅魚圈鋼鐵分公司，鲅魚圈 115007

基金項目:

國家高技術研究發展計劃(863計劃) 2014AA041801-2

詳細信息

通訊作者:
黎敏, E-mail: limin@ustb.edu.cn

中圖分類號: TP277
計量
- 文章訪問數: 1106
- HTML全文瀏覽量: 459
- PDF下載量: 94
- 被引次數: 0
出版歷程
- 收稿日期: 2018-07-23
- 刊出日期: 2019-04-15

Control technology of end-point carbon in converter steelmaking based on functional digital twin model

XU Gang^{1, 2},
LI Min^{2
, ,},
XU Jin-wu²,
JIA Chun-hu³,
CHEN Zhao-fu³

1.
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
2.
Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, China
3.
Ansteel Co., Ltd. Bayuquan Iron and Steel Branch, Bayuquan 115007, China

More Information

Corresponding author: LI Min, E-mail:limin@ustb.edu.cn

摘要

摘要: 由于轉爐冶煉過程中的熱力學和動力學反應復雜，副槍控制模型和傳統的煙氣分析模型存在很大的局限性，導致了轉爐冶煉終點碳含量的預測精度偏低，是實現智能煉鋼的主要技術瓶頸. 針對上述問題，提出了基于煙氣分析的煉鋼過程函數型數字孿生模型. 首先，利用煙氣分析得到連續監測的實時數據，以此來實時監控轉爐熔池內鋼水的碳氧反應狀態; 然后，根據熔池反應所處的不同階段，利用函數型數據分析方法建立吹煉前期和吹煉后期的函數型預測模型; 在此基礎上，按照吹煉前期和吹煉后期這兩個階段來分別自動修正模型中的系數函數，從而能在復雜的實際工況條件下完成對熔池碳含量的準確預測. 通過260 t氧氣轉爐的工業應用實例，證實函數型數字孿生模型具有良好的自學習和自適應能力，對異常冶煉狀態具有良好的魯棒性，可以實現全過程的熔池碳含量動態預測，終點碳質量分數在± 0. 02% 范圍內的命中率為95%. 利用函數型數字孿生模型在拉碳階段對鋼水中碳含量的預測值來控制終吹點. 更為重要的是，在保證入爐原料成分、溫度、質量等參數穩定的前提下，采用該模型可以有望取消基于副槍的停吹取樣步驟，從而降低生產成本，提高產品質量和生產效率，具有廣泛的工業應用前景.
- 轉爐煉鋼 /
- 數字孿生模型 /
- 煙氣分析 /
- 函數型數據分析 /
- 終點碳控制
Abstract: An important part of the iron-and-steel production process, converter steelmaking is the most widely used and efficient method of steelmaking in the world. Under the requirements of"China Manufacturing 2025, "ensuring intelligent steelmaking, improving smelting production efficiency, and reducing production cost are major concerns that should be addressed urgently in converter steelmaking. Owing to the complex thermodynamic and dynamic reactions in the converter smelting process, sublance control and traditional flue-gas analysis models have limitations that result in low prediction accuracy of the end-point carbon in converter smelting, thereby causing the main technical bottleneck in intelligent steelmaking. Therefore, a functional digital twin model of the steelmaking process based on flue-gas analysis was proposed. First, continuously monitored real-time data were obtained by flue gas analysis to observe the carbon and oxygen reaction state of molten steel in the converter. Then, according to various stages of the converter reaction, the functional data analysis method was used to establish the functional prediction models for the early and late stages of blowing. The greatest advantage of the method is that the model can automatically adjust the coefficient function according to the measured off-gas data by using a continuous functional curve to fit the complex dynamic reaction process. Therefore, the proposed model can accurately predict not only the normal smelting process but also the decarburization and carbon drawing process for the secondary scraping slag. An industrial experiment on a 260 t converter was conducted to prove that the functional digital twin model of the converter smelting process has good self-learning and self-adaptive ability and is robust to the abnormal smelting state. Furthermore, the model can predict the carbon content of the converter dynamically in the entire process and the end-point carbon content can reach 95% at ± 0. 02%. Using the predicted value of the carbon content to control the final blowing point through the functional digital twin model can effectively prevent overblowing or underblowing. More importantly, on the premise of guaranteeing the stability of raw material composition, temperature, weight, and other parameters, the model is expected to cancel the blown-off sampling step based on sublance. This feature can reduce the production cost while improving the product quality and production efficiency for a wide range of industrial applications.
- converter steelmaking /
- digital twin model /
- off-gas analysis /
- functional data analysis /
- end-point carbon control

HTML全文

圖 1 冶煉過程中，CO和CO₂含量的變化曲線

Figure 1. Profile of COand CO₂ during the steelmaking process

下載: 全尺寸圖片幻燈片

圖 2 正常情況下煙氣數據實測與擬合曲線

Figure 2. Measured and fitted off-gas profile under normal conditions

下載: 全尺寸圖片幻燈片

圖 3 出現噴濺時煙氣數據實測與擬合曲線

Figure 3. Measured and fitted off-gas profile when slopping occurs

下載: 全尺寸圖片幻燈片

圖 4 二次扒渣過程中煙氣數據曲線

Figure 4. Off-gas profile in two-stage slagging

下載: 全尺寸圖片幻燈片

圖 5 二次扒渣后正常情況下煙氣曲線

Figure 5. Off-gas profile under normal conditions after two-stage slagging

下載: 全尺寸圖片幻燈片

圖 6 二次扒渣后出現噴濺時煙氣曲線

Figure 6. Off-gas profile when slopping occurs after two-stage slagging

下載: 全尺寸圖片幻燈片

圖 7 常規冶煉情況下拉碳階段碳含量對比圖

Figure 7. Carbon comparison in decarburization stage in normal steelmaking

下載: 全尺寸圖片幻燈片

圖 8 二次扒渣情況下拉碳階段碳含量對比圖

Figure 8. Carbon comparison in decarburization stage in two-stage slagging

下載: 全尺寸圖片幻燈片

圖 9 終點碳實測值(TSO) 和模型預測值對比圖

Figure 9. End-point carbon comparison between measured and predicted data

下載: 全尺寸圖片幻燈片

表 1 副槍檢測時(TSC) CO和C質量分數對比表

Table 1. Comparison of COand C content at time of sublance (TSC) testing?%

鋼種	實測CO	預測CO	實測C	預測C
AH32	32. 091	30. 810	0. 223	0. 199
AH32	24. 222	21. 285	0. 425	0. 446
SPHC	22. 578	21. 521	0. 448	0. 463
SPA-H	32. 637	32. 631	0. 269	0. 250
SPHC	22. 571	21. 098	0. 367	0. 394
B	27. 867	25. 655	0. 355	0. 340
SPHC	20. 924	20. 009	0. 406	0. 403
IF	34. 245	33. 411	0. 246	0. 229

下載: 導出CSV

259luxu-164

參考文獻(17)

[1]	Aacatech-National Academy of Science and Engineering. CyberPhysical Systems: Driving Force for Innovations in Mobility, Health, Energy and Production. Berlin: Springer Publishing Company, 2012
[2]	Lee E A.CPS foundations//Design Automation Conference.Anaheim, 2010: 737
[3]	Yin R Y. A discussion on"smart"steel plant-view from physical system side. Iron Steel, 2017, 52(6): 1 https://www.cnki.com.cn/Article/CJFDTOTAL-GANT201706001.htm 殷瑞鈺. 關于智能化鋼廠的討論—從物理系統一側出發討論鋼廠智能化. 鋼鐵, 2017, 52(6): 1 https://www.cnki.com.cn/Article/CJFDTOTAL-GANT201706001.htm
[4]	China Information Physics System Development Forum.White Paper on Information Physics Systems [J/OL].Cyber Physical Systems (2017-03-02) [2018-07-20].http://www.cesi.cn/201703/2251.html 中國信息物理系統發展論壇. 信息物理系統白皮書[J/OL]. 信息物理系統(2017-03-02) [2018-07-20]. http://www.cesi.cn/201703/2251.html
[5]	Zhang C X, Cheng L L, Wang X D. Research on architecture of intelligent manufacturing based on cyber-physical system. Comput Sci, 2013, 40(6A): 37 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA2013S1007.htm 張彩霞, 程良倫, 王向東. 基于信息物理融合系統的智能制造架構研究. 計算機科學, 2013, 40(6A): 37 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA2013S1007.htm
[6]	Sun X Y, Wang X, Wu J W, et al. Prediction-based manufacturing center self-adaptive demand side energy optimization in cyber physical systems. Chin J Mech Eng, 2014, 27(3): 488 doi: 10.3901/CJME.2014.03.488
[7]	Wang L H, T?rngren M, Onori M. Current status and advancement of cyber-physical systems in manufacturing. J Manuf Syst, 2015, 37: 517 doi: 10.1016/j.jmsy.2015.04.008
[8]	Pirvu B C, Zamfirescu C B, Gorecky D. Engineering insights from an anthropocentric cyber-physical system: a case study for an assembly station. Mechatronics, 2016, 34: 147 doi: 10.1016/j.mechatronics.2015.08.010
[9]	Xu G, Zhang X T, Li M, et al. Online monitoring and control method of product quality based on embedded cyber-physical system models. J Mech Eng, 2017, 53(12): 94 https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201712012.htm 徐鋼, 張曉彤, 黎敏, 等. 基于嵌入式CPS模型的產品質量在線管控方法. 機械工程學報, 2017, 53(12): 94 https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201712012.htm
[10]	Wang X H, Li J Z, Liu F G. Technological progress of BOF steelmaking in period of development mode transition. Steelmaking, 2017, 33(1): 1 https://www.cnki.com.cn/Article/CJFDTOTAL-LGZZ201701002.htm 王新華, 李金柱, 劉鳳剛. 轉型發展形勢下的轉爐煉鋼科技進步. 煉鋼, 2017, 33(1): 1 https://www.cnki.com.cn/Article/CJFDTOTAL-LGZZ201701002.htm
[11]	Liao D S, Sun S, Waterfall S, et al.Integrated KOBM steelmaking process control//Oxygen Steelmaking.Beijing, 2015: 107
[12]	Wu L, Jiang Z H, Gong W, et al. Continuous control of BOF by gas analysis. Steelmaking, 2008, 24(1): 12 吳令, 姜周華, 龔偉, 等. 通過煙氣分析實現轉爐連續控制. 煉鋼, 2008, 24(1): 12
[13]	Xie S M, Tao J, Chai T Y. BOF steelmaking endpoint control based on neural network. Control Theory Appl, 2003, 20(6): 903 https://www.cnki.com.cn/Article/CJFDTOTAL-KZLY200306018.htm 謝書明, 陶鈞, 柴天佑. 基于神經網絡的轉爐煉鋼終點控制. 控制理論與應用, 2003, 20(6): 903 https://www.cnki.com.cn/Article/CJFDTOTAL-KZLY200306018.htm
[14]	Yuan P, Mao Z Z, Wang F L. Endpoint prediction of EAF based on multiple support vector machines. J Iron Steel Res Int, 2007, 14(2): 20 doi: 10.1016/S1006-706X(07)60021-1
[15]	Han M, Zhao Y, Yang X L, et al. Endpoint prediction model of basic oxygen furnace steelmaking based on robust relevance vector machines. Control Theory Appl, 2011, 28(3): 343 https://www.cnki.com.cn/Article/CJFDTOTAL-KZLY201103009.htm 韓敏, 趙耀, 楊溪林, 等. 基于魯棒相關向量機的轉爐煉鋼終點預報模型. 控制理論與應用, 2011, 28(3): 343 https://www.cnki.com.cn/Article/CJFDTOTAL-KZLY201103009.htm
[16]	Ramsay J O, Silverman B W. Functional Data Analysis. 2nd Ed. New York: Springer, 2005
[17]	Morris J S. Functional regression. Ann Rev Stat Appl, 2015, 2: 321 doi: 10.1146/annurev-statistics-010814-020413