This article proposes a system for monitoring a blast furnace operation based on DB-Mini-KMeans and multi-layer perceptron (MLP), which solves a difficult problem categorising the furnace operation types. The system uses the correlation between cooling wall temperature and furnace operation type, creates an furnace operation type recognition model with optimised K-Means and MLP algorithms and makes a comparison test with other recognition models; evaluates all kinds of operation types by combining six blast furnace production indexes, such as gas utilisation rate and airflow and establishes a monitoring system of furnace operation types in blast furnaces. The clustering performance of the system has been improved by nearly 40%, and the recognition accuracy of various operation types has reached more than 90%, covering functions such as two-dimensional schematic diagrams of furnace operation types and status warnings, which provide help and support for people to analyse furnace conditions.
LiuRZhaoWGLiuS, et al.Development and discussion of intelligent blast furnace smelting. Iron Steel2023; 58: 1–10.
3.
QiYSChuMSTangJ, et al.Research progress of blast furnace data governance based on big data technology. Metallurg Autom2023; 47: 43–52.
4.
ShiQTangYChuMS. Research progress of intelligent blast furnace ironmaking technology based on industrial big data. J Iron Steel Res2022; 34: 1314–1324.
5.
LuZD. Study on the damage mechanism and longevity of blast furnace lining and cooling stave. Wuhan, Hubei Province, China: Wuhan University of Science and Technology, 2021.
6.
LiuSZhaoYDLiX, et al.An online sintering batching system based on machine learning and intelligent algorithm: instrumentation, controland system engineering. ISIJ Int2021; 61: 2237–2248.
7.
LiHYLiXLiuXJ, et al.Prediction of blast furnace parameters using feature engineering and stacking algorithm. Ironmak Steelmak2022; 49: 283–296.
8.
ShiLWenYBZhaoGS, et al.Recognition of blast furnace gas flow center distribution based on infrared image processing. J Iron Steel Res2016; 23: 203.
9.
ZhangLYJiaoKXZhangL, et al.Prediction of blast furnace fuel ratio based on back-propagation neural network and K-nearest neighbor algorithm. Steel Res Int2022; 93: 102278.
10.
ZhuXZZhangHWYangCJ. MWPCA blast furnace anomaly monitoring algorithm based on Gaussian mixture model. J Chem Ind2021; 72: 1539–1548.
11.
GarcíaFACampoyPMochónJ, et al.A new “user-friendly” blast furnace advisory control system using a neural network temperature profile classifier. ISIJ Int2010; 50: 730–737.
12.
YanBJZhangJLGuoHW, et al.Evaluation of blast furnace operation profile based on principal component analysis. J Northeastern Univ (Nat Sci Edition)2015; 36: 952–956.
13.
LuJYanBJZhaoW, et al.Comparison of clustering effects of blast furnace operation furnace based on different algorithms. J Eng Sci2022; 44: 2081–2089.
14.
DuPLeiMJiangDW, et al.Cluster analysis of blast furnace profile based on cooling stave temperature. Metallurg Autom2023; 47: 109–115.
15.
ChenLKZhouMLWuNY. Development and application of diagnostic management model for operation profile of copper stave blast furnace. Ironmaking2004; 23: 25–29.
16.
WeiZBaiDHWangSW. Monitoring and maintenance of No.8 blast furnace in Shaogang. Ironmaking2013; 32: 7–10.
17.
GuoKN. Data detection techniques based on fusion of improved K-means clustering algorithms. Electron Des Eng2024; 32: 41–45.
18.
ChangweiXJueCXiheQ, et al.GOKA: a network partition and cluster fusion algorithm for controller placement problem in SDN. J Circuits Syst Comput2023; 32: 1–10.
19.
WangXN. Research on life prediction method of blast furnace. Northeast University, 2013.
20.
LiJJHuDCLiuBG, et al.Development and application of big data visualization platform for angang blast furnace. Angang Technol2023: 15–20.
21.
LiuXJZhangYJLiX, et al.Blast furnace temperature monitoring and early warning system based on big data. China Metallurgy2023; 33: 98–105+140.
22.
ZhangZFLiuXJLiX, et al.Prediction of FeO content in sinter based on MIV-GA-BP model. China Metallurgy2022; 32: 75–81.
23.
ZhaoJLiHWLiuXJ, et al.Prediction model of blast furnace permeability index based on Xgboost. China Metallurgy2021; 31: 22–29.
24.
LiWHLiYMBianYX. An improved method of code package hierarchical reconstruction based on DBSCAN algorithm. Comput Eng Sci2021; 43: 689–696.
25.
LuCYDengSMaWB, et al.Cluster federated learning method based on DBSCAN clustering. Comput Sci2022; 49(S1): 232–237.
26.
WangYYangWXiaoXY, et al.Clustering and analysis of power consumption behavior of massive users based on denoising autoencoder network feature dimension reduction and improved small batch optimization K-means algorithm. Electr Power Autom Equip2022; 42: 146–153.
27.
PengKLeung VictorCMHuangQJ. Clustering approach based on Mini batch kmeans for intrusion detection system over big data. IEEE Access2018; 6: 11897–11906.
28.
AnSZhangMRWangCZ, et al.Robust fuzzy rough approximations with kNN granules for semi-supervised feature selection. Fuzzy Sets Syst2023; 461: 108476.
29.
ChenYYShuSWWuH, et al.Inverse distance weighted improved KNN algorithm for defect diagnosis of metal oxide arresters. J Fuzhou Univ (Nat Sci Edition)2022; 50: 635–641.
30.
HashemSSGhobadianBNosratiM, et al.Investigation of factors affecting performance of a downdraft fixed bed gasifier using optimized MLP neural networks approach. Fuel2023; 333(P1): 126249.
31.
ChuYMaoJZZhangXM, et al.Optimization of forming quality of zirconium alloy support frame based on MLP-PSO algorithm. Forg Technol2023; 48: 61–67.
32.
SunJPYuXCWangYQ. Identification method of coal mine gas and coal dust explosion based on spectrogram and SVM. Coal Sci Technol2023; 51: 366–376.
33.
ShiHTGaoTJDingMB, et al.A multi-interval composite short-term wind power prediction method based on trend clustering and decision tree. Acta Energiae Solaris Sinica2022; 43: 333–340.
34.
CaoYJZhangJLGuoHW, et al.Cluster analysis and application of operation type of guofeng No.1 blast furnace based on TwoStep algorithm. Iron Steel2013; 48: 17–22+35.
35.
LiuSLiuXJLyuQ, et al.Comprehensive system based on a DNN and LSTM for predicting sinter composition. Appl Soft Comput J2020; 95(prepublish): 106574.
