|
|
|
| Prediction model of blast furnace hearth activity based on theoretical analysis and intelligent algorithm |
| LIU Xiaojie, WEN Liangyixin, ZHANG Yujie, LI Xin, LIU Ran, LÜ Qing |
| School of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, Hebei, China |
|
|
|
|
Abstract Prolonging the service life, ensuring stable running condition and reducing energy consumption of blast furnace have become the main direction of modern blast furnace production development. In order to achieve these goals, improving the activity of blast furnace hearth is considered to be one of the most important measures. The activity of the hearth can reveal the chemical reaction and thermodynamic conditions inside the blast furnace and help to understand the basic mechanism of the blast furnace smelting process, and reasonable evaluation of hearth activity is of great significance for guiding blast furnace production. Therefore, firstly, based on the process data collected from the blast furnace production site, the activity index of the blast furnace hearth was obtained after pretreatment and calculation. Then, in order to further improve the prediction accuracy, the feature selection method and redundancy analysis were adopted to select the most influential parameter from many parameters as the input parameter. Finally, the Bayesian optimization XGBoost model was used to predict the hearth activity by regression, and the regression effect of XGBoost model with default hyperparameters and random forest model was compared. The results show that the Bayesian optimization XGBoost model has excellent performance in predicting the hearth activity, the model has good generalization and nonlinear fitting ability, and the prediction effect is good. The research results provide a strong decision basis for blast furnace production, which can help optimize operating parameters, improve smelting efficiency and reduce energy consumption.
|
|
Received: 14 September 2023
|
|
|
|
| [1] |
郑玉春. 2016年世界钢铁生产与市场情况分析[J]. 中国钢铁业,2017(6):5.(ZHENG Y C. Analysis of world steel production and market situation in 2016[J]. Chinese Steel Industry,2017(6):5.)
|
| [2] |
刘然,赵伟光,刘颂,等. 高炉冶炼智能化的发展与探讨[J]. 钢铁,2023,58(5):10.(LIU R,ZHAO W G,LIU S,et al. Development and discussion of intelligent blast furnace smelting[J]. Iron and Steel,2023,58(5):1.)
|
| [3] |
黄东辉. 钢铁企业高炉炼铁的稳定生产[J]. 中国冶金,2015,25(1):16.(HUANG D H. Stable production of blast furnace ironmaking in iron and steel enterprises[J]. China Metallurgy,2015,25(1):16.)
|
| [4] |
王雪楠. 高炉寿命预测方法研究[D]. 沈阳:东北大学,2013.(WANG X N. Research on Life Prediction Method of Blast Furnace[D]. Shenyang:Northeastern University,2013.)
|
| [5] |
邓勇,刘然,刘小杰,等. 炉缸炭砖侵蚀过程及基于AHP的界面反应调控[J]. 钢铁,2020,55(8):175.(DENG Y,LIU R,LIU X J,et al. Corrosion process of furnace hearth carbon brick and interfacial reaction regulation based on AHP[J]. Iron and Steel,2020,55(8):175.)
|
| [6] |
任玉明,李长武,张建良,等. 关于高炉长寿若干关键问题及对策解析[J]. 山东冶金,2022,44(3):19.(REN Y M,LI C W,ZHANG J L,et al. Analysis of some key problems and countermeasures on blast furnace longevity[J]. Shandong Metallurgy,2022,44(3):19.)
|
| [7] |
金觉生,陶卫忠. 长期高煤比生产炉缸活跃的实践[J]. 宝钢技术,2002(3):13.(JIN J S,TAO W Z. Active practice of furnace hearth in long-term high coal ratio production[J]. Baosteel Technology,2002(3):13.)
|
| [8] |
张贺顺,马洪斌. 首钢2号高炉炉缸工作状态探析[J]. 炼铁,2009(4):10.(ZHNAG H S,MA H B. Analysis on the working state of No.2 blast furnace hearth in Shougang[J]. Ironmaking,2009(4):10.)
|
| [9] |
张玉柱,田欣,赵军,等. 唐钢3 200 m3高炉炉缸活性问题初探[J]. 河北冶金,2010(1): 35.(ZHANG Y Z,TIAN X,ZHAO J,et al. Preliminary study on hearth activity of 3 200 m3 blast furnace in Tangsteel[J]. Hebei Metallurgy,2010(1):35.)
|
| [10] |
DAI B,SUN H J,OU J S,et al. Development and practice of Rist operating line calculation model for blast furnace[J]. Metallurgical Industry Automation,2016,40(2):25.
|
| [11] |
RAIPALA K. Deadman and hearth phenomena in the blast furnace[J]. Scandinavian Journal of Metallurgy,2000,29(1):39.
|
| [12] |
徐万仁,张永忠,吴铿. 高炉炉缸活性状态的表征及改善途径[J]. 炼铁,2010,29(3):23.(XU W R,ZHANG Y Z,WU Q. Characterization of active state of blast furnace hearth and ways to improve it[J]. Ironmaking,2010,29(3):23.)
|
| [13] |
张笑凡. 基于最大信息系数与岭回归的炉缸活性预测[D]. 马鞍山:安徽工业大学,2020.(ZHANG X F. Prediction of Furnace Hearth Activity based on Maximum Information Coefficient and Ridge Regression[D]. Maanshan:Anhui University of Technology,2020.)
|
| [14] |
刘小杰,邓勇,李欣,等. 基于大数据技术的高炉铁水硅含量预测[J]. 中国冶金,2021,31(2):10.(LIU X J,DENG Y,LI X,et al. Prediction of silicon content of blast furnace molten iron based on big data technology[J]. China Metallurgy,2021,31(2):10.)
|
| [15] |
徐锋,方彦军. 基于贝叶斯优化XGBoost的现场校验仪误差预测[J]. 电测与仪表,2019,56(18):120.(XU F,FANG Y J. Error prediction of field calibrator based on Bayesian optimization XGBoost[J]. Electrical Measurement and Instrumentation,2019,56(18):120.)
|
| [16] |
代兵,龙红明,季益龙,等. 一种高炉炉缸活性的量化评价方法:安徽省,CN110343794A[P]. 2019-10-18.(DAI B,LONG H M,JI Y L,et al. A quantitative evaluation method for blast furnace hearth activity:Anhui Province,CN110343794A [P].2019-10-18.)
|
| [17] |
代兵,梁科,王学军,等. 高炉炉缸活性量化计算模型的开发与实践[J]. 中国冶金,2015,25(12):45.(DAI B,LIANG K,WANG X J,et al. Development and practice of quantitative calculation model of blast furnace hearth activity[J]. China Metallurgy,2015,25(12):45.)
|
| [18] |
DENG Y,LIU R,LI T,et al. The quantitative model of hearth activity based on data mining and characteristics of deadman[J]. Metallurgical Research and Technology,2023,120(1):110.
|
| [19] |
刘小杰,张玉洁,李欣,等. 基于大数据的高炉炉温监测预警系统[J]. 中国冶金,2023,33(2):98.(LIU X J,ZHANG Y J,LI X,et al. Blast furnace temperature monitoring and early warning system based on big data[J]. China Metallurgy,2023,33(2):98.)
|
| [20] |
赵军,李红玮,刘小杰,等. 基于XGBoost的高炉透气性指数预测模型[J]. 中国冶金,2021,31(3):22.(ZHAO J,LI H W,LIU X J,et al. Prediction model of blast furnace permeability index based on XGBoost[J]. China Metallurgy,2021,31(3):22.)
|
| [21] |
王帅,李强. 联合大数据和神经网络的高炉透气性预报模型[J]. 钢铁,2023,58(7):46.(WANG S,LI Q. Prediction model of blast furnace permeability by combining big data with neural network[J]. Iron and Steel,2023,58(7):46.)
|
| [22] |
林奕夫,郑书生. 基于正态分布规则的时间差数据清洗算法[J]. 电子技术与软件工程,2021(24):194.(LIN Y F,ZHENG S S. Time difference data cleaning algorithm based on normal distribution rules[J]. Electronic Technology and Software Engineering,2021(24):194.)
|
| [23] |
张诚,刘文. 基于Grubbs通信系统试验数据处理[J]. 中国新通信,2018,20(22):17.(ZHANG C,LIU W. Test data processing based on Grubbs communication system[J]. China New Communications,2018,20(22):17.)
|
| [24] |
HOAGLIN D C,MOSTELLER F,TURKEY J. Understanding Robust and Exploratory Data Analysis[M]. New York:Wiley,1983.
|
| [25] |
王惯玉. 基于数据挖掘方法的炉缸活性预测[D]. 马鞍山:安徽工业大学,2020.(WANG G Y. Prediction of Furnace Hearth Activity based on Data Mining Method[D]. Maanshan:Anhui University of Technology,2020.)
|
| [26] |
ZHANG Z H,CHENG Y,LIU N C. Comparison of the effect of mean-based method and z-score for field normalization of citations at the level of Web of Science subject categories[J]. Scientometrics,2014,101(3):1679.
|
| [27] |
张文政. 高炉炉缸活性的分析探讨[J]. 山东冶金,2022,44(1):21.(ZHANG W Z. Analysis and discussion on the activity of blast furnace hearth[J]. Shandong Metallurgy,2022,44(1):21.)
|
| [28] |
赵运建,邹忠平,牛群,等. 一种定量评价高炉炉缸活跃指数的方法:中国,CN202010917810.9[P]. 2020-12-22.(ZHAO Y J,ZHOU Z P,NIU Q,et al. A method for quantitatively evaluating the activity index of a blast furnace hearth:China,CN202010917810.9[P]. 2020-12-22.)
|
| [29] |
张伟阳,刘小杰,李宏扬,等. 基于大数据技术的炉缸状态可视化[J]. 钢铁,2021,56(7):38.(ZHANG W Y,LIU X J,LI H Y,et al. Visualization of furnace hearth state based on Big Data Technology [J]. Iron and Steel,2021,56(7):38.)
|
| [30] |
李郅琴,杜建强,聂斌,等. 特征选择方法综述[J]. 计算机工程与应用,2019,55(24):10.(LI Z Q,DU J Q,NIE B,et al. Review of feature selection methods[J]. Computer Engineering and Applications,2019,55(24):10.)
|
| [31] |
施启军,潘峰,龙福海,等. 特征选择方法研究综述[J]. 微电子学与计算机,2022,39(3):1.(SHI Q J,PAN F,LONG F H,et al. Review of feature selection methods[J]. Microelectronics and Computer,2022,39(3):1.)
|
| [32] |
代兵,梁科,王学军,等. 高炉合理鼓风动能与炉缸活性的关系[J]. 钢铁,2016,51(2):22.(DAI B,LIANG K,WANG X J,et al. Relationship between reasonable blast energy and hearth activity of blast furnace[J]. Iron and Steel,2016,51(2):22.)
|
| [33] |
黄跟平,周培,李挺,等. 高炉煤气利用率与燃料消耗关系浅析[J]. 现代冶金,2019,47(3):31.(HUANG G P,ZHOU P,LI T,et al. Analysis on the relationship between blast furnace gas utilization rate and fuel consumption[J]. Modern Metallurgy,2019,47(3):31.)
|
| [34] |
RESHEF D N,RESHEF Y A,FINUCANE H K,et al. Detecting novel associations in large data sets[J]. Science,2011,334(6062):1518.
|
| [35] |
ZHANG Y L,SHANG P. KM-MIC:An improved maximum information coefficient based on K-Medoids clustering[J]. Communications in Nonlinear Science and Numerical Simulation,2022,111:106418.
|
| [36] |
贾晓芬,郭永存,黄友锐,等. 基于斯皮尔曼等级相关性的彩色图像椒盐噪点检测算法[J]. 中国科学技术大学学报,2019,49(1):63.(JIA X F,GUO Y C,HUANG Y R,et al. Salt and pepper noise detection algorithm for color images based on Spearman rank correlation[J]. Journal of University of Science and Technology of China,2019,49(1):63.)
|
| [37] |
兰文宝,车畅,陶成云. 基于斯皮尔曼等级相关的单演谱成分选择及其在SAR目标识别中的应用[J]. 电波科学学报,2020,35(3):414.(LAN W B,CHE C,TAO C Y. Single spectral component selection based on Spearman rank correlation and its application in SAR target recognition[J]. Chinese Journal of Radio Science,2019,35(3):414.)
|
| [38] |
贾科,杨哲,魏超,等. 基于斯皮尔曼等级相关系数的新能源送出线路纵联保护[J]. 电力系统自动化,2020,44(15):103.(JIA K,YANG Z,WEI C,et al. New energy transmission line longitudinal protection based on Spearman rank correlation coefficient[J]. Automation of Electric Power Systems,2020,44(15):103.)
|
| [39] |
VU D H,MUTTAQI K M,AGALGAONKAR A P. A variance inflation factor and backward elimination based robust regression model for forecasting monthly electricity demand using climatic variables[J]. Applied Energy,2015,140:385.
|
| [40] |
CHEN T Q,CARLOS G. XGBoost:A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA:[s.n.],2016:785.
|
| [41] |
徐树乔. 基于XGBoost的Bagging方法的电信客户流失预测应用研究[D]. 广州:华南理工大学,2019.(XU S Q. Application of Bagging Method based on XGBoost in Telecom Customer Churn Prediction[D]. Guangzhou:South China University of Technology,2019.)
|
| [42] |
崔佳旭,杨博. 贝叶斯优化方法和应用综述[J]. 软件学报,2018,29(10):3068.(CUI J X,YANG B. Review of Bayesian optimization methods and applications[J]. Journal of Software,2018,29(10):3068.)
|
| [43] |
贾皓阳,钱宇. 基于贝叶斯优化XGBoost算法的变压器故障诊断[J]. 黄河水利职业技术学院学报,2023,35(2):37.(JIA H Y,QIAN Y. Transformer fault diagnosis based on Bayesian optimization XGBoost algorithm[J]. Journal of Yellow River Conservancy Technical Institute,2023,35(2):37.)
|
| [44] |
李亚茹. 面向超参数估计的贝叶斯优化算法研究[D]. 杭州:浙江科技学院,2021.(LI Y R. Research on Bayesian Optimization Algorithm for Hyperparameter Estimation [D]. Hangzhou:Zhejiang University of Science and Technology,2021.)
|
| [45] |
杜岩,王义铭,张田,等. 基于贝叶斯优化XGBoost模型的热轧中厚板终冷温度预测[J]. 轧钢,2022,39(6):91.(DU Y,WANG Y M,ZHANG T,et al. Prediction of final cold temperature of hot rolled medium thick plate based on Bayesian optimization XGBoost model[J]. Steel Rolling,2022,39(6):91.)
|
| [46] |
李红玮,李欣,刘小杰,等. 基于大数据挖掘的钒钛高炉综合运行状态评价模型[J]. 钢铁,2023,58(10):51. LI H W,LI X,LIU X J,et al. Evaluation model for comprehensive operation condition of vanadium and titanium blast furnace based on big data mining[J]. Iron and Steel,2023,58(10):51.)
|
| [47] |
王子. 基于数据挖掘的炉缸活性预测[D]. 合肥:安徽工业大学,2021.(WANG Z. Hearth Activity Prediction based on Data Mining [D]. Hefei:Anhui University of Technology,2021.)
|
| [48] |
张英,邢相栋,周小辉,等. 基于BP网络模型预测高炉炉缸活性的方法:山东省,CN115034370A[P]. 2022-09-09.(ZHANG Y,XING X D,ZHOU X H,et al. Prediction method of Blast furnace hearth activity based on BP network model:Shandong Province,CN115034370A[P]. 2022-09-09.)
|
|
|
|
2024, Vol. 34 
