基于支持向量回歸與極限學習機的高爐鐵水溫度預測

王振陽; 江德文; 王新東; 張建良; 劉征建; 趙寶軍

doi:10.13374/j.issn2095-9389.2020.05.28.001

基于支持向量回歸與極限學習機的高爐鐵水溫度預測

doi: 10.13374/j.issn2095-9389.2020.05.28.001

1.
北京科技大學冶金與生態工程學院，北京 100083
2.
河鋼集團有限公司鋼鐵技術研究總院，石家莊 050023
3.
昆士蘭大學化學工程學院，圣盧西亞 QLD 4072

基金項目: 中國博士后科學基金面上資助項目（2019M650490）

詳細信息

通訊作者:
E-mail: wangzhenyang@ustb.edu.cn

中圖分類號: TF543.1
計量
- 文章訪問數: 1598
- HTML全文瀏覽量: 777
- PDF下載量: 139
- 被引次數: 0
出版歷程
- 收稿日期: 2020-05-28
- 刊出日期: 2021-04-26

Prediction of blast furnace hot metal temperature based on support vector regression and extreme learning machine

1.
School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China
2.
Iron and Steel Technology Research Institute, Hegang Group Co. Ltd., Shijiazhuang 050023, China
3.
School of Chemical Engineering, The University of Queensland, St Lucia QLD 4072, Australia

More Information

Corresponding author: E-mail: wangzhenyang@ustb.edu.cn

摘要

摘要: 選取某4000 m³級別高爐2014年至2019年時間范圍內的日平均數據，以鐵水溫度為目標函數，首先對鐵水溫度的特征參量進行線性與非線性相關性分析、特征選擇與規范化處理，獲取了顯著影響鐵水溫度的正負相關性特征參量。在此基礎上，基于支持向量回歸與極限學習機兩種算法對鐵水溫度構建預測模型，模型均可對鐵水溫度實現有效預測，基于支持向量回歸算法構建的預測模型較優，預測平均絕對誤差為4.33 ℃，±10 ℃誤差范圍內的命中率為94.0%。
- 大數據 /
- 機器學習 /
- 支持向量回歸 /
- 極限學習機 /
- 鐵水溫度
Abstract: The hot metal temperature is a key process parameter for blast furnace (BF) ironmaking that reflects the quality of hot metal, the thermal state of BF hearth, the energy utilization efficiency of BF, and many other information. Prediction of the hot metal temperature in the next smelting cycle will be helpful in gaining a better understanding of the change trend of hot metal quality and BF smelting status in time. With this, corresponding operational measures can be conducted to maintain the BF stable and smooth state, high production, and low consumption. Nowadays, big data technology has made considerable progress toward a more accurate and faster collection, storage, transmission, query, analysis, and integration of mass data, providing a good data foundation for data-driven machine learning models. In addition, with the substantial increase in computer calculation speed and the significant development of algorithms, the prediction accuracy of deep machine learning models has noticeably improved. The development of these technologies provides feasibility for the prediction of important indicators under complex industrial conditions. Based on the data produced from a 4000-m³ BF in a large span time range (2014–2019) and daily time dimension, this paper considered hot metal temperature as the objective function. First, the characteristic parameters of hot metal temperature were processed by linear and nonlinear correlation analysis, feature selection, and normalization methods. Then, the positive and negative correlation characteristic parameters that have a significant influence on the temperature of the hot metal were obtained. Finally, prediction models of hot metal temperature were established based on two algorithms of support vector regression and extreme learning machine. Although both the algorithms can achieve effective prediction, results from support vector regression are better at an average absolute error of 4.33 °C and a hit rate of 94.0% (±10 °C).
- big data /
- machine learning /
- support vector regression /
- extreme learning machine /
- hot metal temperature

HTML全文

圖 1 鐵水溫度初選特征參量樣本散點圖

Figure 1. Scatter plot of the primary characteristic parameters of hot metal temperature

下載: 全尺寸圖片幻燈片

圖 2 鐵水溫度與初選特征參量之間相關系數。（a）Pearson相關系數；（b）Spearman相關系數

Figure 2. Correlation coefficient between hot metal temperature and primary characteristic parameters: (a) Pearson; (b) Spearman

下載: 全尺寸圖片幻燈片

圖 3 鐵水溫度測量值與預測值比對。（a）基于SVR算法；（b）基于ELM算法

Figure 3. Comparison of measured and predictive values of hot metal temperature：(a) prediction value based on support vector regression (SVR)；(b) prediction value based on extreme learning machine (ELM).

下載: 全尺寸圖片幻燈片

圖 4 鐵水溫度預測值與測量值偏差。（a）基于SVR的鐵溫預測值與測量值偏差；（b）基于ELM的鐵溫預測值與測量值偏差；（c）基于SVR與ELM預測鐵溫誤差概率密度分布函數

Figure 4. Deviation of predictive value of hot metal temperature from the measured value: (a) based on SVR; (b) based on ELM; (c) the probability density distribution function of hot metal temperature error based on SVR and ELM

下載: 全尺寸圖片幻燈片

圖 5 鐵水溫度預測的百分比誤差散點分布統計圖。（a）SVR;（b）ELM

Figure 5. Scatter distribution statistics of percentage error in hot metal temperature prediction: (a) SVR; (b) ELM

下載: 全尺寸圖片幻燈片

表 1 鐵水溫度預測的初選特征參量

Table 1. Primary data items for hot metal temperature prediction

Operating parameters	State parameters
Blast volume	Volume utilization coefficient
Blast pressure	Synthetic load
Blast temperature	Gas utilization efficiency
Blast velocity energy	Daily hot metal production
Coke rate	Pressure difference
Coal injection rate	Permeability index
Nut coke rate	Bosh gas volume
Fuel rate	Bosh gas index
Oxygen enrichment	Cooling water temperature difference
Pulverized coal injection per hour	Current hot metal temperature
Theoretical combustion temperature	Hot metal Si content

下載: 導出CSV

表 2 鐵水溫度終選特征參量

Table 2. Final characteristic parameters of hot metal temperature

No.	Characteristic parameters
1	Fuel rate
2	Nut coke rate
3	Coke rate
4	Blast temperature
5	Bosh gas index
6	Permeability index
7	Hot metal Si content
8	Daily hot metal production
9	Current hot metal temperature
10	Synthetic load
11	Pressure difference
12	Gas utilization efficiency
13	Volume utilization coefficient
14	Cooling water temperature difference

下載: 導出CSV

表 3 SVR與ELM算法鐵水溫度預測結果綜合定量表征

Table 3. Quantitative characterization of SVR and ELM model prediction results of hot metal temperature

Model	MAPE/%	MAE /℃	RMSE/℃	HP(±10 ℃)/%
SVR	0.29	4.33	5.60	94.0
ELM	0.31	4.69	6.09	88.5

下載: 導出CSV

259luxu-164

參考文獻(25)

[1]	Wang Z Y, Zhang J L, Liu Z J, et al. Status, technological progress, and development directions of the ironmaking industry in China. Ironmaking Steelmaking, 2019, 46(10): 937 doi: 10.1080/03019233.2019.1697111
[2]	Wang Z Y, Zhang J L, An G, et al. Analysis on the oversize blast furnace desulfurization and a sulfide capacity prediction model based on congregated electron phase. Metall Mater Trans B, 2016, 47(1): 127 doi: 10.1007/s11663-015-0462-3
[3]	Martin R D, Obeso F, Mochon J, et al. Hot metal temperature prediction in blast furnace using advanced model based on fuzzy logic tools. Ironmaking Steelmaking, 2007, 34(3): 241 doi: 10.1179/174328107X155358
[4]	Jimenez J, Mochon J, de Ayala J S, et al. Blast furnace hot metal temperature prediction through neural networks-based models. ISIJ Int, 2004, 44(3): 573 doi: 10.2355/isijinternational.44.573
[5]	Ding Z Y, Zhang J, Liu Y. Ensemble non-Gaussian local regression for industrial silicon content prediction. ISIJ Int, 2017, 57(11): 2022 doi: 10.2355/isijinternational.ISIJINT-2017-251
[6]	Gao C H, Chen J M, Zeng J S, et al. A chaos-based iterated multistep predictor for blast furnace ironmaking process. AIChE J, 2009, 55(4): 947 doi: 10.1002/aic.11724
[7]	Cui G M, Li J, Zhang Y, et al. Prediction modeling study for blast furnace hot metal temperature based on T-S fuzzy neural network model. Iron Steel, 2013, 48(11): 11 崔桂梅, 李靜, 張勇, 等. 基于T-S模糊神經網絡模型的高爐鐵水溫度預測建模. 鋼鐵, 2013, 48(11):11
[8]	Cui G M, Cheng S. Predictive modeling of blast furnace temperature by using distributed neural network model. J Iron Steel Res, 2014, 26(6): 27 崔桂梅, 程史. 基于分布式神經網絡模型的高爐爐溫預測建模. 鋼鐵研究學報, 2014, 26(6):27
[9]	Shi L, Tang J J, Yu T, et al. Parameters prediction on furnace temperature on blast furnace based on a nonlinear spline transform-PLS. J Iron Steel Res, 2013, 25(2): 20 石琳, 湯佳佳, 于濤, 等. 基于樣條變換的非線性PLS的反應高爐爐溫的參數預測. 鋼鐵研究學報, 2013, 25(2):20
[10]	Zhang X M, Kano M, Matsuzaki S. A comparative study of deep and shallow predictive techniques for hot metal temperature prediction in blast furnace ironmaking. Comput Chem Eng, 2019, 130: 106575 doi: 10.1016/j.compchemeng.2019.106575
[11]	Zhang X M, Kano M, Matsuzaki S. Ensemble pattern trees for predicting hot metal temperature in blast furnace. Comput Chem Eng, 2019, 121: 442 doi: 10.1016/j.compchemeng.2018.10.022
[12]	Diaz J, Fernandez F J, Prieto M M. Hot metal temperature forecasting at steel plant using multivariate adaptive regression splines. Metals, 2020, 10(1): 41
[13]	Hashimoto Y, Sawa Y, Kano M. Online prediction of hot metal temperature using transient model and moving horizon estimation. ISIJ Int, 2019, 59(9): 1534 doi: 10.2355/isijinternational.ISIJINT-2019-101
[14]	Su X L, Zhang S, Yin Y X, et al. Prediction model of hot metal temperature for blast furnace based on improved multi-layer extreme learning machine. Int J Mach Learn Cybern, 2019, 10(10): 2739 doi: 10.1007/s13042-018-0897-3
[15]	Zhao H, Zhao D T, Yue Y J, et al. Study on prediction method of hot metal temperature in blast furnace // IEEE International Conference on Mechatronics and Automation. Takamatsu, 2017: 316.
[16]	Wang Y K, Liu X Y, Zhang B L. On feature selection and blast furnace temperature tendency prediction in hot metal based on SVM-RFE // Australian and New Zealand Control Conference. Melbourne, 2018: 371.
[17]	Yue Y J, Dong A, Zhao H, et al. Study on prediction model of blast furnace hot metal temperature // IEEE International Conference on Mechatronics and Automation. Harbin, 2016: 1396.
[18]	Liu Y, Gao Z. Enhanced just-in-time modelling for online quality prediction in BF ironmaking. Ironmaking Steelmaking, 2015, 42(5): 321 doi: 10.1179/1743281214Y.0000000229
[19]	Guo D W, Zhou P. Soft-sensor modeling of silicon content in hot metal based on sparse robust LS-SVR and multi-objective optimization. Chin J Eng, 2016, 38(9): 1233 郭東偉, 周平. 基于稀疏化魯棒LS-SVR與多目標優化的鐵水硅含量軟測量建模. 工程科學學報, 2016, 38(9):1233
[20]	Zhang H G, Zhang S, Yin Y X. Multi-class fault diagnosis of BF based on global optimization LS-SVM. Chin J Eng, 2017, 39(1): 39 張海剛, 張森, 尹怡欣. 基于全局優化支持向量機的多類別高爐故障診斷. 工程科學學報, 2017, 39(1):39
[21]	Chu F, Ye J F, Ma X P, et al. Online performance prediction of CCPP byproduct coal-gas system based on online sequential extreme learning machine. Chin J Eng, 2016, 38(6): 861 褚菲, 葉俊鋒, 馬小平, 等. 基于OS-ELM的CCPP副產煤氣燃料系統在線性能預測. 工程科學學報, 2016, 38(6):861
[22]	Li A L, Zhao Y M, Cui G M. Prediction model of blast furnace temperature based on ELM with grey correlation analysis. J Iron Steel Res, 2015, 27(11): 33 李愛蓮, 趙永明, 崔桂梅. 基于灰色關聯分析的ELM高爐溫度預測模型. 鋼鐵研究學報, 2015, 27(11):33
[23]	Chen H Z, Yang J P, Lu X C, et al. Quality prediction of the continuous casting bloom based on the extreme learning machine. Chin J Eng, 2018, 40(7): 815 陳恒志, 楊建平, 盧新春, 等. 基于極限學習機(ELM)的連鑄坯質量預測. 工程科學學報, 2018, 40(7):815
[24]	Chen P, Li Q, Zhang D Z, et al. A survey of multimodal machine learning. Chin J Eng, 2020, 42(5): 557 陳鵬, 李擎, 張德政, 等. 多模態學習方法綜述. 工程科學學報, 2020, 42(5):557
[25]	Tunckaya Y. Performance assessment of permeability index prediction in an ironmaking process via soft computing techniques. Proc Inst Mech Eng Part E-J Process Mech Eng, 2017, 231(6): 1101 doi: 10.1177/0954408916654199