Modeling of oxygen delignification process using a Kriging-based algorithm

被引:0
作者
Euler, Gladson [1 ]
Nayef, Girrad [1 ]
Fialho, Danyelle [1 ]
Brito, Romildo [1 ]
Brito, Karoline [1 ]
机构
[1] Univ Fed Campina Grande, Chem Engn Dept, Campus Univ, BR-58109970 Campina Grande, Paraiba, Brazil
关键词
Kraft process; Cellulose; Pre-bleaching; Gaussian process regressor; Kriging; GAUSSIAN PROCESS REGRESSION; PREDICTION;
D O I
10.1007/s10570-020-02991-4
中图分类号
TB3 [工程材料学]; TS [轻工业、手工业、生活服务业];
学科分类号
0805 ; 080502 ; 0822 ;
摘要
A phenomenological model of cellulose production processes presents limitations due to the presence of species and chemical reactions of complex computational representation. Modeling based on machine learning techniques is an alternative to overcome this drawback. This paper addresses the Gaussian process regressor (Kriging) method to model the oxygen delignification process in one of the largest pulp production plants of the world. Different correlation models were used to evaluate this method; furthermore, an optimization routine, based on the constrained optimization by linear approximation method, was coupled to model to minimize the objective function, which is based on the input cost. Results have shown the good performance of using a combined Kriging method with optimization routines in the non-linear industrial processes to obtain a representative model capable of providing optimized operating scenarios. A reduction of 36.5% in consumption of NaOH was obtained, while required restrictions are obeyed. Graphic abstract
引用
收藏
页码:2485 / 2496
页数:12
相关论文
共 17 条
[1]   Developing a predictive model for nanoimprint lithography using artificial neural networks [J].
Akter, Tahmina ;
Desai, Salil .
MATERIALS & DESIGN, 2018, 160 :836-848
[2]  
[Anonymous], 2011, INT C PROC AUT CONTR, DOI DOI 10.1109/PACC.2011.5979038
[3]   A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees [J].
De Caigny, Arno ;
Coussement, Kristof ;
De Bock, Koen W. .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2018, 269 (02) :760-772
[4]  
Hall, 2016, EVOLUTION ANAL OPPOR
[5]  
Krige D.G., 1951, J. South. Afr. Inst. Min. Metall., V52, P119
[6]   Development of an optimized trend kriging model using regression analysis and selection process for optimal subset of basis functions [J].
Lee, Hakjin ;
Lee, Duck-Joo ;
Kwon, Hyungil .
AEROSPACE SCIENCE AND TECHNOLOGY, 2018, 77 :273-285
[7]   Wind power prediction with missing data using Gaussian process regression and multiple imputation [J].
Liu, Tianhong ;
Wei, Haikun ;
Zhang, Kanjian .
APPLIED SOFT COMPUTING, 2018, 71 :905-916
[8]   Multi-objective optimization of cyclone separators in series based on computational fluid dynamics [J].
Luciano, Rafaello D. ;
Silva, Barbara L. ;
Rosa, Leonardo M. ;
Meier, Henry F. .
POWDER TECHNOLOGY, 2018, 325 :452-466
[9]   Mixed-effects Gaussian process modeling approach with application in injection molding processes [J].
Luo, Linkai ;
Yao, Yuan ;
Gao, Furong ;
Zhao, Chunhui .
JOURNAL OF PROCESS CONTROL, 2018, 62 :37-43
[10]   Use of kriging models to approximate deterministic computer models [J].
Martin, JD ;
Simpson, TW .
AIAA JOURNAL, 2005, 43 (04) :853-863