Optimal estimation of physical properties of the products of an atmospheric distillation column using support vector regression

被引：17

作者：

Serfidan, Ahmet Can ^{[1
,2
]}

Uzman, Firat ^{[1
,2
]}

Turkay, Metin ^{[2
]}

机构：

[1] TUPRAS, Petrol Cad 25, TR-41780 Kocaeli, Turkey

[2] Koc Univ, Rumelifeneri Yolu, TR-34450 Istanbul, Turkey

来源：

COMPUTERS & CHEMICAL ENGINEERING | 2020年 / 134卷

关键词：

Data analytics; Optimization; Parameter estimation; Support vector regression; Atmospheric distillation; OPTIMIZATION; UNIT; MULTICOMPONENT; MACHINE; DESIGN;

D O I：

10.1016/j.compchemeng.2019.106711

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Atmospheric distillation column is one of the most important units in an oil refinery where crude oil is fractioned into its more valuable constituents. Almost all of the state-of-the art online equipment has a time lag to complete the physical property analysis in real time due to complexity of the analyses. Therefore, estimation of the physical properties from online plant data with a soft sensor has significant benefits. In this paper, we estimate the physical properties of the hydrocarbon products of an atmospheric distillation column by support vector regression using Linear, Polynomial and Gaussian Radial Basis Function kernels and SVR parameters are optimized by using a variety of algorithms including genetic algorithm, grid search and non-linear programming. The optimization-based data analytics approach is shown to produce superior results compared to linear regression, the mean testing error of estimation is improved by 5% with SVR 4.01 degrees C to 3.8 degrees C. (C) 2020 Elsevier Ltd. All rights reserved.

引用

页数：12

共 50 条

[21] Support Vector Regression and Genetic Algorithm for HVAC Optimal Operation [J].

Chen, Ching-Wei ;

Chang, Yung-Chung .

MATHEMATICAL PROBLEMS IN ENGINEERING, 2016, 2016

[22] Conceptual Quantities Estimation Using Bootstrapped Support Vector Regression Models [J].

Idowu, Oluwafunmibi Seun ;

Lam, Ka Chi .

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT, 2020, 146 (04)

[23] Using tabu search to configure support vector regression for effort estimation [J].

A. Corazza ;

S. Di Martino ;

F. Ferrucci ;

C. Gravino ;

F. Sarro ;

E. Mendes .

Empirical Software Engineering, 2013, 18 :506-546

[24] Using tabu search to configure support vector regression for effort estimation [J].

Corazza, A. ;

Di Martino, S. ;

Ferrucci, F. ;

Gravino, C. ;

Sarro, F. ;

Mendes, E. .

EMPIRICAL SOFTWARE ENGINEERING, 2013, 18 (03) :506-546

[25] Composite support vector quantile regression estimation [J].

Shim, Jooyong ;

Hwang, Changha ;

Seok, Kyungha .

COMPUTATIONAL STATISTICS, 2014, 29 (06) :1651-1665

[26] Location estimation via support vector regression [J].

Wu, Zhi-Li ;

Li, Chun-hung ;

Ng, Joseph Kee-Yin ;

Leung, Karl R. P. H. .

IEEE TRANSACTIONS ON MOBILE COMPUTING, 2007, 6 (03) :311-321

[27] Optic flow estimation by support vector regression [J].

Colliez, Johan ;

Dufrenois, Franck ;

Hamad, Denis .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2006, 19 (07) :761-768

[28] Composite support vector quantile regression estimation [J].

Jooyong Shim ;

Changha Hwang ;

Kyungha Seok .

Computational Statistics, 2014, 29 :1651-1665

[29] Estimation of diffusion coefficients from voltammetric signals by support vector and gaussian process regression [J].

Bogdan, Martin ;

Brugger, Dominik ;

Rosenstiel, Wolfgang ;

Speiser, Bernd .

JOURNAL OF CHEMINFORMATICS, 2014, 6

[30] Volatility Forecasting Using Support Vector Regression and a Hybrid Genetic Algorithm [J].

Santamaria-Bonfil, Guillermo ;

Frausto-Solis, Juan ;

Vazquez-Rodarte, Ignacio .

COMPUTATIONAL ECONOMICS, 2015, 45 (01) :111-133

← 1 2 3 4 5 →