Operation Parameters Optimization of Blast Furnaces Based on Data Mining and Cleaning

doi:10.12068/j.issn.1005-3026.2020.08.015

Abstract

Abstract: Effective mining of mass production data helps to improve the productivity and the level of management to realize “smart steel works”. The production data for the last 4 years of one steel works were collected， and the box plot was used to clean the data to improve their quality. Twenty-three characteristic parameters affecting hot metal quality and yield were selected by technological theory and expertise combined with the random forest algorithm. Hot metal yield and Si+Ti content were taken as the objective parameters， which could be divided into three categories by k-means cluster analysis. Thirteen parameters contributing to the wide range fluctuation of hot metal yield and quality were obtained after the comprehensive analysis of classification results and characteristic parameters， and the reasonable variable ranges of corresponding parameters were provided. The research can guide the stable operation of blast furnaces and the application of data mining in the iron and steel industry.

Key words: smart steel works, data mining, feature engineering, k-means clustering, random forest, blast furnace

CLC Number:

TF572

LIU Xin， ZHANG Wei-jun， SHI Quan， ZHOU Le. Operation Parameters Optimization of Blast Furnaces Based on Data Mining and Cleaning[J]. Journal of Northeastern University Natural Science, 2020, 41(8): 1153-1160.

References

[1]张寿荣，于仲洁.中国炼铁技术60年的发展［J］.钢铁，2014，49(7):8-14.(Zhang Shou-rong，Yu Zhong-jie.Development of ironmaking technology in the past 60 years［J］.Iron and Steel，2014，49(7):8-14.)
[2]周渝生，曹传根，甘菲芳.高炉长寿技术的最新进展［J］.钢铁，2003，38(11):70-74，8.(Zhou Yu-sheng，Cao Chuan-gen，Gan Fei-fang.Recent development of BF long-campaign technology［J］.Iron and Steel，2003，38(11):70-74，8.)
[3]徐雪松，杨胜杰.大数据背景下中国钢铁生产能源管控路径优化研究［J］.工业技术经济，2017，36(1):32-40.(Xu Xue-song，Yang Sheng-jie.The optimization of iron and steel enterprises energy management under the background of big data［J］.Journal of Industrial Technological Economics，2017，36(1):32-40.)
[4]王钧超.大数据时代产业经济信息分析及在宏观决策中的应用［D］.北京:中国地质大学，2016.(Wang Jun-chao.Analysis of industrial economic information and its application in macro decision in the era of big data.［D］.Beijing:China University of Geosciences，2016.)
[5]Krumeich J，Werth D，Loos P，et al.Advanced planning and control of manufacturing processes in steel industry through big data analytics:case study and architecture proposal［C/OL］//IEEE International Conference on Big Data.Washington DC，2014［2019-08-25］.https://ieeexplore.ieee.org/document/7004408.
[6]Guo S，Yu J X，Liu X J，et al.A predicting model for properties of steel using the industrial big data based on machine learning［J］.Computational Materials Science，2019，160:95-104.
[7]Kang L，Du H L，Zhang H，et al.Systematic research on the application of steel slag resources under the background of big data［J/OL］.Complexity，2018［2019-08-05］.https://www.hindawi.com/journals/complexity/2018/6703908/.
[8]中冶京诚全流程大数据分析系统探索智慧钢铁［N］.世界金属导报，2018-11-27.(The whole process of big data analysis system to explore the wisdom of steel—CERI［N］.World Metal Report，2018-11-27.)
[9]白瑞国，徐立山，包阔，等.大数据过程质量控制系统在钢铁生产中的应用［J］.中国冶金，2018，28(8):76-80.(Bai Rui-guo，Xu Li-shan，Bao Kuo，et al.Application of big data process quality control system in iron and steel production［J］.China Metallurgy，2018，28(8):76-80.)
[10]Brandenburger J，Colla V，Nastasi G，et al.Big data solution for quality monitoring and improvement on flat steel production［J］.IFAC:Papers On Line，2016，49(20):55-60.
[11]Han Y，Li J，Yang X L，et al.Dynamic prediction research of silicon content in hot metal driven by big data in blast furnace smelting process under Hadoop cloud platform［J/OL］.Complexity，2018［2019-08-25］.https://doi.org/10.1155/2018/8079697.
[12]Hua C，Wu J，Li J，et al.Silicon content prediction and industrial analysis on blast furnace using support vector regression combined with clustering algorithms［J］.Neural Computing and Applications，2017，28(12):4111-4121.
[13]吕庆，刘月明，张振峰，等.基于承钢生产数据预测烧结矿FeO含量［J］.钢铁研究学报，2018，30(12):957-962.(Lyu qing，Liu Yue-ming，Zhang Zhen-feng，et al.Prediction of FeO content in sinter based on production data of Chengde Steel Mill［J］.Journal of Iron and Steel Research，2018，30(12):957-962.)
[14]吕庆，刘颂，刘小杰，等.基于大数据技术的烧结全产线质量智能控制系统［J］.钢铁，2018，53(7):1-9.(Lyu qing，Liu song，Liu Xiao-jie，et al.Intelligent control system based on big data technology for whole production line of sintering quality［J］.Iron and Steel，2018，53(7):1-9.)
[15]马富涛，张建良，张磊，等.铁前数模技术进展与大数据应用探讨［J］.钢铁，2018，53(12):1-9.(Ma Fu-tao，Zhang Jian-liang，Zhang lei，et al.Introduction of development and progress of mathematical modeling technology in iron-making area and discussion on application prospects of big data technology［J］.Iron and Steel，2018，53(12):1-9.)
[16]Dixon B E，Duke J，Grannis S.Measuring and improving the quality of data used for syndromic surveillance［J］.Online Journal of Public Health Informatics，2017，9(1):182-189.
[17]Genuer R，Poggi J M，Malot C T.Variable selection using random forests［J］.Pattern Recognition Letters，2010，31(14):2225-2236.
[15]关守平，房少纯.一种新型的区间-粒子群优化算法［J］.东北大学学报(自然科学版)，2012，33(10):1381-1384.(Guan Shou-ping，Fang Shao-chun.A new interval particle swarm optimization algorithm［J］.Journal of Northeastern University(Natural Science)，2012，33(10):1381-1384.)