基于机理、数据和知识的大型高炉冶炼过程建模研究

doi:10.16183/j.cnki.jsjtu.2018.10.002

摘要/Abstract

摘要： 高炉冶炼过程具有强非线性、大时滞和欠调节的特性，其内部为多相多场耦合的复杂动态系统，仅单一地从机理角度构建高炉模型或简单地利用高炉数据建模很难达到较好的效果.为此，利用新型高炉传感器所测数据，并结合高炉冶炼机理、运行数据和专家经验构建了几个高炉局部模型.几个模型都以高炉实际数据进行了测试，并且成果已运行于柳钢2号高炉之上.

关键词: 高炉冶炼, 建模, 数据, 铁水质量, 布料控制

Abstract: Blast furnace smelting process is characterized by strong nonlinearity, large time delay and under regulation, and its interior is a complex dynamic system with multiphase and multi field coupling. Therefore, it is difficult to achieve a reliable blast furnace model by only mechanism modeling or simply data driven modeling. Based on the measured data of a new type of blast furnace sensor, and combining the blast furnace smelting mechanism, operation data and expert experience, several local models of blast furnace have been built. The models have been tested by actual data of blast furnace and the results are running on the No. 2 BF of Liuzhou Iron and Steel Company.

Key words: blast furnace smelting, modeling, data, quality of molten iron, burden distribution control

中图分类号:

TP 18

李军朋1，华长春1，关新平2. 基于机理、数据和知识的大型高炉冶炼过程建模研究[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1142-1154.

LI Junpeng,HUA Changchun,GUAN Xinping. Modeling Research for Blast Furnace Smelting Process Based on Smelting Mechanism, Operation Data and Expert Knowledge[J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1142-1154.

参考文献

［1］张玉柱, 胡长庆. 炼铁节能与工艺计算［M］. 北京: 冶金工业出版社, 2002. ZHANG Yuzhu, HU Changqing. Energy saving and process calculation of ironmaking［M］. Beijing: Metallurgical Industry Press, 2002. ［2］王筱留. 钢铁冶金学(炼铁部分)［M］. 2版.北京: 冶金工业出版社, 2000. WANG Xiaoliu. Metallurgy of iron and steel (ironmaking part) ［M］. 2nd ed. Beijing: Metallurgical Industry Press, 2000. ［3］刘祥官, 刘芳. 高炉炼铁过程优化与智能控制系统［M］. 北京: 冶金工业出版社, 2003. LIU Xiangguan, LIU Fang. Optimization of ironmaking process and intelligent control system for blast furnace［M］. Beijing: Metallurgical Industry Press, 2003. ［4］郜传厚, 刘祥官. 高炉冶炼过程的混沌性辨识. I. 饱和关联维数的确定［J］. 金属学报, 2004, 40(4): 347-350. GAO Chuanhou, LIU Xiangguan. Chaotic identification of BF ironmaking process. I. The calculation of Saturated correlative dimension［J］. Acta Metallurgica Sinica, 2004, 40(4): 347-350. ［5］罗世华, 曾九孙. 基于多分辨分析的高炉铁水含硅量波动多重分形辨识［J］. 物理学报, 2009, 58(1): 150-157. LUO Shihua, ZENG Jiusun. Multi-fractal identification of the fluctuation of silicon content in blast furnace hot metal based on multi-resolution analysis［J］. Acta Physica Sinica, 2009, 58(1): 150-157. ［6］李爱莲, 赵永明, 崔桂梅. 基于数据预处理与智能优化的高炉铁液温度预测模型的研究［J］. 铸造技术, 2015, 36(2): 450-454. LI Ailian, ZHAO Yongming, CUI Guimei. Study on temperature prediction model of blast furnace hot metal based on data preprocessing and intelligent optimization［J］. Foundry Technology, 2015, 36(2): 450-454. ［7］毕学工. 高炉过程数学模型及计算机控制［M］. 北京: 冶金工业出版社, 1996. BI Xuegong. The mathematical model and computer control of the blast furnace process［M］. Beijing: Metallurgical Industry Press, 1996. ［8］DE CASTRO J A, NOGAMI H, YAGI J. Transient mathematical model of blast furnace based on multi-fluid concept, with application to high PCI operation［J］. ISIJ International, 2000, 40(7): 637-646. ［9］NOGAMI H, CHU M, YAGI J. Multi-dimensional transient mathematical simulator of blast furnace process based on multi-fluid and kinetic theories［J］. Computers and Chemical Engineering, 2005, 29(11/12): 2438-2448. ［10］BAMBAUER F, WIRTZ S, SCHERER V, et al. Transient DEM-CFD simulation of solid and fluid flow in a three dimensional blast furnace model［J］. Powder Technology, 2018, 334: 53-64. ［11］PANDIT S M, CLUM J A, WU S M. Modeling, prediction and control of blast furnace operation from observed data by multivariate time series［C］∥Proceedings of the 34th Ironmaking Conference. Toronto, Canada: AIME, 1975: 403-416. ［12］姬田冒孝, 西尾通卓, 西川洁, 等. 统计制御理论(ARMA法)の高炉炉热制御べの适用［J］.钢铁, 1980, 66(4): 96. ADACHI Putian, TOSHIKI Nishio, NORIKO Nishikawa, et al. On the blast furnace operation control using statistical method (Ironmaking) ［J］. Iron and Steel, 1980, 66(4): 96. ［13］VANHATALO E. Multivariate process monitoring of an experimental blast furnace［J］. Quality and Reliability Engineering International, 2010, 26(5): 495-508. ［14］BHATTACHARYA T. Prediction of silicon content in blast furnace hot metal using partial least squares (PLS) ［J］. ISIJ International, 2005, 45(12): 1943-1945. ［15］CHEN W, WANG B X, HAN H L. Prediction and control for silicon content in pig iron of blast furnace by integrating artificial neural network with genetic algorithm［J］. Ironmaking and Steelmaking, 2009, 37(6): 458-463. ［16］SAXN H, PETTERSSON F, GUNTURU K. Evolving nonlinear time-series models of the hot metal silicon content in the blast furnace［J］. Materials and Manufacturing Processes, 2007, 22(5): 577-584. ［17］JIAN L, GAO C, LI L, et al. Application of least squares support vector machines to predict the silicon content in blast furnace hot metal［J］. ISIJ International, 2008, 48(11): 1659-1661. ［18］SAXN H, GAO C, GAO Z. Data-driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace—A review［J］. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2213-2225. ［19］GAO C, GE Q, JIAN L. Rule extraction from fuzzy-based blast furnace SVM multiclassifier for decision-making［J］. IEEE Transactions on Fuzzy Systems, 2014, 22(3): 586-596. ［20］刘学艺, 刘祥官, 王文慧. 贝叶斯网络在高炉铁水硅含量预测中的应用［J］. 钢铁, 2005, 40(3): 17-20. LIU Xueyi, LIU Xiangguan, WANG Wenhui. Application of Bayesian network to predicting silicon content in hot metal［J］. Iron and Steel, 2005, 40(3): 17-20. ［21］JIAN L, GAO C. Binary coding SVMs for the multiclass problem of blast furnace system［J］. IEEE Transactions on Industrial Electronics, 2013, 60(9): 3846-3856. ［22］GAO C, JIAN L, LUO S. Modeling of the thermal state change of blast furnace hearth with support vector machines［J］. IEEE Transactions on Industrial Electronics, 2012, 59(2): 1134-1145. ［24］NAITO M, TAKEDA K, MATSUI Y. Ironmaking technology for the last 100 years: Deployment to advanced technologies from introduction of technological know-how, and evolution to next-generation process［J］. ISIJ International, 2015, 55(1): 7-35. ［25］BI X, TORSSELL K, WIJK O. Simulation of the blast furnace process by a mathematical model［J］. ISIJ International, 1992, 32(4): 470-480.

[1]	陈昌川, 刘凯, 刘仁光, 冯晓棕, 覃延佳, 代少升, 张天骐. 基于多源局部放电信号数据流聚类分离方法[J]. 上海交通大学学报, 2022, 56(8): 1014-1023.
[2]	李幸芝, 韩蓓, 李国杰, 汪可友, 徐晋. 分布式绿色能源碳交易机制及碳数据管理的挑战[J]. 上海交通大学学报, 2022, 56(8): 977-993.
[3]	王箫剑, 洪君, 陈晶华, 李鸿光. 基于参数化建模和响应面优化的箱体减重研究[J]. 空天防御, 2022, 5(4): 60-66.
[4]	胡金硕, 黄健哲. 共轴双旋翼动力学建模与验证[J]. 上海交通大学学报, 2022, 56(3): 395-402.
[5]	邓晨, 孔轶男, 汪清, 陈功. 一种融合物理规律的经验工程修正算法研究[J]. 空天防御, 2022, 5(3): 73-79.
[6]	马航宇, 周笛, 卫宇杰, 吴伟, 潘尔顺. 变工况下基于自适应深度置信网络的轴承智能故障诊断[J]. 上海交通大学学报, 2022, 56(10): 1368-1377.
[7]	胡滨, 何强, 武亚涛, 孙清洋, 刘云申. 机载双基地雷达空时二维杂波建模与特性分析[J]. 空天防御, 2022, 5(1): 37-44.
[8]	张恒睿. 需求导向的材料设计[J]. 上海交通大学学报, 2021, 55(Sup.1): 93-94.
[9]	巩伟峥, 许凌, 姚寅. 计及风速分布与机组惯量转化不确定性的风电场可用惯量估计[J]. 上海交通大学学报, 2021, 55(S2): 51-59.
[10]	胡益恺, 王春香, 杨明. 智能车辆决策方法研究综述[J]. 上海交通大学学报, 2021, 55(8): 1035-1048.
[11]	何夏维, 蔡云泽, 严玲玲. 一种合成残差式的反作用轮故障检测方法[J]. 上海交通大学学报, 2021, 55(6): 716-728.
[12]	宋邓强, 周彬, 申兴旺, 鲍劲松, 周亚勤. 面向船舶分段制造过程的动态知识图谱建模方法[J]. 上海交通大学学报, 2021, 55(5): 544-556.
[13]	赵会盼, 刘环宇. 基于多模态数据融合学习网络的微弱目标群检测方法[J]. 空天防御, 2021, 4(3): 41-47.
[14]	陈永信. 滑翔飞行器气动外形与轨迹一体化设计优化[J]. 空天防御, 2021, 4(3): 76-84.
[15]	李同德, 严怀成, 周革, 范莎, 洪君. 异步多速率多传感器网络及在导航制导中的分布式融合估计[J]. 空天防御, 2021, 4(3): 92-98.