All Issue

2022 Vol.54, Issue 4 Preview Page
Soft Sensing and Multi-objective Optimization of Pulp Washing Process Based on Data-Driven Technology
Wen-juan Shan1†
,
Bing Liu2
,
Wei Tang3
1Faculty of Science, Xi’an Aeronautical Institute, Ph.D., Lecturer
2Huawei Technologies Co. Ltd., Master, Engineer
3School of Electrical and Control Engineering, Shaanxi University of Science & Technology, Professor
†Corresponding author: E-Mail: swj0230@126.com (Address: Xi’an Aeronautical Institute, No. 259, West 2nd Ring Road, Lianhu District, Xi’an City, Shaanxi Province, China)
30 August 2022. pp. 57-74
PDF XML Citation
Abstract

Due to the multi-variable, time-delay, and nonlinear characteristics of the pulp washing process, it is difficult to accurately measure and optimize the process. An asymmetrical nonlinear control system can be decomposed into a group of low-dimensional subsystems, which brings great convenience to the analysis and design of the system. In this paper, the concept of symmetry is used to simplify nonlinear optimal control problems, and data-driven theory is used to solve optimal policy problems. This paper proposes a data-driven operating model optimization method to model and optimizes the pulp washing process. The most important quality indicators of pulp washing performance are the alkali residue in washing pulp and the Baumé degree of the extracted black liquor. Considering the difficulty of modeling, online measurement of these indicators, two-step neural network, and multiple logistic regression were used to build a prediction model for soda water and Baumé degree. The mathematical model of the washing process can be identified, and the indicators meet the production requirements. With the goal of better product quality, low cost, and low energy consumption, based on the optimized operation mode database, the ant colony optimization (ACO) algorithm was used to solve the multi-objective problem. Theoretical analysis and practical application were carried out, and the optimal control system of the pulp washing process was designed. The actual results showed that the pulp output was increased by 20%, and the water consumption was reduced by nearly 30%. This method is effective during pulp washing.

Keywords
Pulp washing
data-driven
neural network
dynamic modeling
principal component analysis
References

Literature Cited

1

Yang, C. J., Sun,Y. X. and Bao, B. L., The present and future of the pulp washing process control, China Pulp &Paper, 2(25):14-19 (1998).

2

Tang,W. and Shi, S. J., Pulp washing process DCS based on double-objective optimization, Control Theory and Applications, 4(4):555-560 (2002).

3

Gui,W. H., Yang, C. H. and Li, Y. G., Data-driven operational-pattern optimization for copper flash smelting process, Acta Automatica Sinica 3(35):718-723 (2009).

10.3724/SP.J.1004.2009.00717
4

Yan, A. J., Chai,T. Y. and Yue, H., Multivariable intelligent optimizing control approach for shaft furnance roasting process, Acta Automatica Sinica 6(4):636-640 (2006).

5

Cao, P. F. and Luo, X. L., Modeling of soft sensor for chemical process, CIESC Journal 5(64):789-801 (2013).

6

Xie, S. M., Gao, X. W. and Chai, T. Y., BOF end point prediction based on grey model, Journal of Iron and Steel Research 4(23):25-29 (1999).

7

Zhao, S. J., Zhang, J. and Xu, Y. M., Monitoring of processes with multiple operating modes through multiple principle component analysis models, Ind Eng Chen Res 3(43):7025-7030 (2004).

10.1021/ie0497893
8

Du, Z. G., Wang, G. Q. and Zhang, Y. G., Application of BP neural networks in predicting the product yield of HVGO steam cracking, Ethylene Industry 2(12):8-11 (2009).

9

Kun, H. Z., Hua, G. W. and Qi, P. X., Intelligent optimization of optimal operational pattern in the process of copper converting furnace, Control Theory and Applications 2(21):243-247 (2005).

10

Jiang, P. F., Gu, X. P. and Chen, X., Parameter estimation of large-scale industrial process model with multiple operating points, Computers and Applied Chemistry 7(27):46-50 (2010).

11

Hu, E. L. and Wang, B., A new optimization in SDP-based learning, Neurocomputing 7(365):10-20 (2019).

10.1016/j.neucom.2019.06.058
12

Yao, K. T., Shao, Z. J. and Chen, X., Data-driven technology and mechanism model based soft sensor modeling in PTA process, Computers and Applied Chemistry, 8(10):1388-1394 (2010) .

13

Tang, W., Wang, M. X., He, L. F. and Itoh, H., Neural network based double-objective optimization and application to pulp washing process improvement, Industrial & Engineering Chemistry Research, 6(46):5015-5020 (2007).

10.1021/ie070275o
14

Cherkassky, V. and Ma, Y. Q., Practical selection of SVM parameters and noise estimation for SVM regression, Neural Networks 1(23):113-127 (2004).

10.1016/S0893-6080(03)00169-2
15

Zhu, P. F., Xia, L.Y. and Pan, H. T., Multi-model fusion modeling method based on improved Kalman filtering algorithm, CIESC Journal 1(66):1388-1394 (2015).

16

Han, F., Han, A. and Hao, J., Saliency detection method using hypergraphs on adaptive multiscales, IEEE Access 2(23):245-255 (2018).

10.1109/ACCESS.2018.2797880
17

Li, Z. and Cai, J. J., Application of the soft measurement technology to optimization system of boiler burning at power station, The Chinese Journal of Process Engineering 3(6):49-55 (2004).

18

Liu, H., Liu, Z. J. and Li, H. G., A data-driven approach to chemical process alarm threshold optimization, CIESC Journal 2(63):2372-2378 (2012).

19

Li, X. F., Mei, C. and Xiao, T. Y., Numerical simulation, analysis of Guixi copper flash smelting furnace, Rare Metals 5(4):260-265 (2002).

20

Hyunsuk, N. and Roman, L., Security-aware multi-objective optimization of distributed reconfigurable embedded systems, Journal of Parallel and Distributed Computing 2(133):377-390 (2019).

10.1016/j.jpdc.2018.02.015
21

Jiang, H. B. and Zhang, J. L., Properties and structural optimization of pulverized coal for blast furnace injection, Journal of Iron and Steel Research 2(3):06-12 (2011).

10.1016/S1006-706X(11)60029-0
22

Tang, W., Wang, M. X., Chao,Y. Y., He, L. F. and Itoh, H., Double-objective optimization for a pulp washing process based on neural network, 2007 International Conference on Mechatronics and Automation, Harbin, China, 5-8 Aug. (2007).

10.1109/ICMA.2007.4303613
Information
  • Publisher :Korea Technical Association of The Pulp and Paper Industry
  • Publisher(Ko) :한국펄프종이공학회
  • Journal Title :Journal of Korea TAPPI
  • Journal Title(Ko) :펄프종이기술
  • Volume : 54
  • No :4
  • Pages :57-74
  • Received Date : 2022-03-10
  • Revised Date : 2022-08-02
  • Accepted Date : 2022-08-04
  • DOI :https://doi.org/10.7584/JKTAPPI.2022.08.54.4.57
Journal Informaiton Journal of Korea TAPPI Journal of Korea TAPPI
Online Submission
  • scopus
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
Journal Informaiton Journal Informaiton - close