Soft sensor model for endpoint carbon content and temperature in BOF steelmaking based on just-in-time learning with multilayer structure preservation and sparse information enhancement

Abstract

Ensuring precise prediction of the endpoint carbon content and temperature is paramount in controlling the endpoint of the basic oxygen furnace (BOF) steelmaking process. However, due to the frequent fluctuations in real-time blowing conditions, the conventional just-in-time learning soft sensor approach encounters challenges in effectively anticipating the blowing endpoint. To address these aforementioned issues, this research introduces a novel approach known as the pattern-oriented multilayer structure preservation and sparse information enhancement model (POMLSP-SIE). This approach involves dynamically generating a dataset with the same distribution based on the characteristics of the query sample pattern. It is combined with a multi-pathway dimension reduction model to preserve multi-view spatial geometry information while reducing data dimension. The low-dimensional embedding serves as dictionaries containing various hierarchical structural characteristics. Significant information within these dictionaries is sparsely represented to amplify its influence during the regression prediction process while diminishing the impact of less relevant information. This refinement aims to rectify the problem of static regression models being weak to adapt to changing working conditions, ultimately enhancing prediction performance. The effectiveness of the proposed method is substantiated through an experimental study utilising real converter steelmaking process data, thereby confirming its practical applicability.

Keywords

BOF steelmaking endpoint soft sensor just-in-time dimension reduction

Get full access to this article

View all access options for this article.

References

. The simulation of multiphase flow behavior in BOF. Liaoning, China: University of Science and Technology Liaoning, 2018.

Zhang

. 500 Questions about Converter Steelmaking, p. 415. Bei Jing: Chemical Industry Press, 2009.

Yang

Liu

Chen

. Just-in-time updating soft sensor model of endpoint carbon content and temperature in BOF steelmaking based on deep residual supervised autoencoder. Chemom Intell Lab Syst 2022; 231: 104679.

Zhou

Zhao

Chen

. Endpoint prediction of BOF by flame spectrum and furnace mouth image based on fuzzy support vector machine. OPTIK 2019; 178: 575–581.

Wang

. Research on end-point control technology of converter steelmaking. China Met Bull 2022; 2022: 138–140.

Wen

Zhou

. Current status and application of converter end-point control technology. Modern Ind Econ Inform 2019; 9: 79–81.

. Discussion on the application status of end-point control technology in converter steelmaking. Metallurg Mater 2020; 40: 121–190.

Lei

, et al. Endpoint control technology for BOF steelmaking. Steelmaking 2011; 27: 66–70.

. Research on real-time prediction method of endpoint carbon content in converter steelmaking based on flame image recognition. Kunming University of Science and Technology 2021: 80.

10.

Liu

Zhao

. A real-time prediction method of carbon content in converter steelmaking based on QCN flame image feature extraction. Contr Theory Appl 2022; 39: 1745–1757.

11.

Shao

Zhao

Chen

, et al. Applying flame spectral analysis and multi-class classification algorithm on the BOS endpoint carbon content prediction. OPTIK 2015; 126: 4539–4543.

12.

Shao

Zhou

Chen

, et al. BOF endpoint prediction based on the flame radiation by hybrid SVC and SVR modeling. OPTIK 2014; 125: 2491–2496.

13.

Han

Jiang

. Endpoint prediction model of basic oxygen furnace steelmaking based on PSO-ICA and RBF neural network. Dalian, China: IEEE, 2010.

14.

Zhang

. Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network. J Process Control 2018; 66: 51–58.

15.

Liu

Cheng

Liu

. Prediction model of BOF end-point temperature and carbon content based on PCA-GA-BP neural network. Metallurg Res Technol 2022; 119: 605.

16.

X. D, J. W, S. Y. Predictive Model of BOF Based on LM-BP Neural Network Combining with Learning Rate[Z], 2009.

17.

Xie

Sun

Chen

. BOF endpoint prediction based on RBF neural network. J Shenyang Univ Technol 2006; 04: 405–408.

18.

Liping

Zhang

Yongyin

. Research on BOF steelmaking endpoint control based on neural network, 2012.

19.

Alakent

. Online tuning of predictor weights for relevant data selection in just-in-time-learning. Chemom Intell Lab Syst 2020; 203: 104043.

20.

Wang

Han

Wang

. Applying input variables selection technique on input weighted support vector machine modeling for BOF endpoint prediction. Eng Appl Artif Intell 2010; 23: 1012–1018.

21.

H. Y. A just-in-time learning approach for sewage treatment process monitoring with deterministic disturbances, 2015.

22.

Liu

Xiong

, et al. Just-in-time-learning based prediction model of BOF endpoint carbon content and temperature via vMF mixture model and weighted extreme learning machine. Comput Chem Eng 2021; 154: 107488.

23.

Yang

Pedrycz

, et al. Clustering time series under trend-oriented fuzzy information granulation. Appl Soft Comput 2023; 141: 110284.

24.

J. B, D. N, T. C, W. G, E. R. Neural Network for Nonlinear Dimension Reduction Through Manifold Recovery, 2019.

25.

J. D, Q. Q, C. G, X. C. BOF steelmaking endpoint prediction based on FWA-TSVR, 2017.

26.

Luo

. Process monitoring with global–local preserving projections. Ind Eng Chem Res 2014; 53: 7696–7705.

27.

Islam M

Xing

. Geometry and statistics-preserving manifold embedding for nonlinear dimensionality reduction. Pattern Recogn Lett 2021; 151: 155–162.

28.

T. G, H. C, W. C. HTGCE: an graph-based and classifier-oriented dimension reduction method for multisource heterogeneous feature tensors. IEEE Trans Geosci Remote Sens 2022; 60: 1–18.

29.

Luo

Bao

Mao

, et al. Nonlocal and local structure preserving projection and its application to fault detection. Chemom Intell Lab Syst 2016; 157: 177–188.

30.

Zhan

Yang

. Enhanced fault detection based on ensemble global local preserving projections with quantitative global local structure analysis. Ind Eng Chem Res 2017; 56: 10743–10755.

31.

Bao

Luo

Mao

, et al. Improved fault detection and diagnosis using sparse global-local preserving projections. J Process Control 2016; 47: 121–135.

32.

Chai

. Industrial process control systems: research status and development direction. Chin Sci (Inf Sci) 2016; 46: 1003–1015.

33.

Xiaoqiang

Yongfei

. An improved KPCA algorithm of chemical process fault diagnosis based on RVM. Xian, China: TCCT, CAA, 2013.

34.

Chen

Cai

, et al. An optimized feature extraction algorithm for abnormal network traffic detection. Future Gener Comput Syst 2023; 149: 330–342.

35.

Zhang

Chen

, et al. Rapid detection of lignin content in corn straw based on Laplacian eigenmaps. Infrared Phys Technol 2023; 133: 104787.

36.

Luo

Bao

Mao

, et al. Nonlinear process monitoring using data-dependent kernel global–local preserving projections. Ind Eng Chem Res 2015; 54: 11126–11138.

37.

Wang

Liu

Guo

. Adaptive sliding window LSTM NN based RUL prediction for lithium-ion batteries integrating LTSA feature reconstruction. Neurocomputing 2021; 466: 178–189.

38.

Sun

. A review on data-driven process monitoring methods: characterization and mining of industrial data. Processes 2022; 10: 335.

39.

Xiong

. Research on soft measurement method of carbon temperature at blowing end point based on integrated learning of converter steelmaking production process data. Kunming, China: Kunming University of Science and Technology, 2021, 83.

40.

Zhao

Liu

Chen

, et al. Soft sensor method of endpoint carbon content and temperature of BOF steelmaking based on CJS-SLLE and just-in-time learning. Control Theory Appl 2023; 40(10): 1–11.