Data-driven just-in-time learning based adaptive predictive control for blast furnace ironmaking

被引:1
作者
Yi C.-M. [1 ]
Zhou P. [1 ]
Chai T.-Y. [1 ]
机构
[1] State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, 110819, Liaoning
来源
Zhou, Ping (zhouping@mail.neu.edu.cn) | 2020年 / South China University of Technology卷 / 37期
关键词
Blast furnaces; Data-driven; Industrial data exceptions; Just-in-time learning (JITL); Linearization; Model predictive control;
D O I
10.7641/CTA.2019.80689
中图分类号
学科分类号
摘要
In this paper, a data-driven adaptive predictive control method based on just-in-time learning (JITL-APC) is proposed for blast furnace ironmaking process. The feature of the proposed approach is that the controller uses the k-vector nearest neighbor (k-VNN) strategy to search the input/output (I/O) data information in the database to establish the local model for the nonlinear system, and then calculates the control law based on the local model. Moreover, we introduce an industrial data exception handling mechanism in this method to fill or replace the abnormal data items by using the average data items in the JITL learning subset to eliminate the influence of abnormal data on the control system. Meanwhile, a JITL model retention strategy (MRS) is proposed to avoid the serious mismatch of local models caused by insufficient data samples in the database. In addition, JITL-APC updates the database by collecting I/O data in real time, so that the controller can smoothly adapt to different working conditions. MRS can also effectively suppress the influence of noise interference and improve the stability of the control system. Finally, industrial experiments have been carried out on the 2# blast furnace in a larger Iron & Steel Group Co. of China, which proves the validity of this method. © 2020, Editorial Department of Control Theory & Applications. All right reserved.
引用
收藏
页码:295 / 306
页数:11
相关论文
共 25 条
[1]  
Zhou P., Yuan M., Wang H., Et al., Multivariable dynamic modeling for molten iron quality using online sequential random vector functional-link networks with self-feedback connections, Information Sciences, 325, 1, pp. 237-255, (2015)
[2]  
Wu X., Shen J., Li Y., Et al., Data-driven modeling and predictive control for boiler-turbine unit, IEEE Transactions on Energy Conversion, 28, 20, pp. 470-481, (2013)
[3]  
Saint-Donat J., Bhat N., Mcavoy T.J., Neural net based model predictive control, International Journal of Control, 54, 6, pp. 1453-1468, (1991)
[4]  
Pottmann M., A nonlinear predictive control strategy based on radial basis function models, Computers & Chemical Engineering, 21, 9, pp. 965-980, (1997)
[5]  
Chu J.Z., Tsai W.Y., Jang S.S., Et al., Multistep Model Predictive Control Based on Artificial Neural Networks, Industrial and Engineering Chemistry Research, 42, 21, pp. 5215-5228, (2003)
[6]  
Zhou P., Guo D.W., Wang H., Et al., Data-driven robust M-LS-SVR-based NARX modeling for estimation and control of molten iron quality indices in blast furnace ironmaking, IEEE Transactions on Neural Networks and Learning Systems, 29, 9, pp. 4007-4021, (2018)
[7]  
Tang X., Zhuang L., Jiang C., Prediction of silicon content in hot metal using support vector regression based on chaos particle swarm optimization, Expert Systems with Applications, 36, 9, pp. 11853-11857, (2009)
[8]  
Lu C.H., Tsai C.C., Generalized predictive control using recurrent fuzzy neural networks for industrial processes, Journal of Process Control, 17, 1, pp. 83-92, (2007)
[9]  
Zhou P., Li R., Guo D., Et al., Multi-output support vector regression modeling for multivariate molten iron quality indices in blast furnace ironmaking process, Control Theory & Applications, 33, 6, pp. 727-734, (2016)
[10]  
Guo J., Chen Q., Zhu R., Et al., Adaptive predictive control of a class of nonlinear system, Control Theory & Applications, 19, 1, pp. 68-72, (2002)