An Artificial Intelligence Method for Energy Efficient Operation of Crude Distillation Units under Uncertain Feed Composition

被引:19
作者
Durrani, Muhammad Amin [1 ]
Ahmad, Iftikhar [1 ]
Kano, Manabu [2 ]
Hasebe, Shinji [3 ]
机构
[1] Natl Univ Sci & Technol NUST, Sch Chem & Mat Engn, Sect H12, Islamabad 44000, Pakistan
[2] Kyoto Univ, Grad Sch Informat, Dept Syst Sci, Sakyo Ku, Kyoto 6068501, Japan
[3] Kyoto Univ, Dept Chem Engn, Nishikyo Ku, Kyoto 6158510, Japan
关键词
crude distillation unit; energy efficiency; Taguchi method; genetic algorithm; artificial neural networks; ROBUST OPTIMIZATION APPROACH; NEURAL-NETWORKS; GENETIC ALGORITHM; REFINERY; STATE; MODEL;
D O I
10.3390/en11112993
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The crude distillation unit (CDU) is one of the most energy-intensive processes of a petroleum refinery. The composition of crude is subject to change on regular basis. The uncertainty in crude oil composition causes wastage of a substantial amount of energy in the CDU operation. In this study, a novel approach based on a multi-output artificial neural networks (ANN) model was devised to cope with variations (uncertainty) in crude composition. The proposed method is an extended version of another method of cut-point optimization based on hybridization of Taguchi and genetic algorithm. A data comprised of several hundred variations of crude compositions and their optimized cut point temperatures, derived from the hybrid approach, was used to train the ANN model. The proposed method was validated on a simulated CDU flowsheet for a Pakistani crude, i.e., Zamzama. The proposed method is faster and computationally less expensive than the hybrid method. In addition, it can efficiently predict optimum cut point temperatures for any variant of the crude composition.
引用
收藏
页数:12
相关论文
共 32 条
[1]   Dimensions and Analysis of Uncertainty in Industrial Modeling Process [J].
Ahmad, Iftikhar ;
Kano, Manabu ;
Hasebe, Shinji .
JOURNAL OF CHEMICAL ENGINEERING OF JAPAN, 2018, 51 (07) :533-543
[2]   Integration of Nonlinear Crude Distillation Unit Models in Refinery Planning Optimization [J].
Alattas, Abdulrahman M. ;
Grossmann, Ignacio E. ;
Palou-Rivera, Ignasi .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2011, 50 (11) :6860-6870
[3]  
Ali S.F., 2012, Int. J. Eng. Technol, V12, P36
[4]  
Bolf N., 2008, P 2008 16 MED C CONT
[5]  
Brooks RW, 1999, HYDROCARB PROCESS, V78, P53
[6]  
Brueske S., 2015, Bandwidth study on energy use and potential energy savings opportunities in U.S. petroleum refining
[7]  
Cabello J.J., 2017, P 6 INT WORKSH ADV C
[8]   On-line estimation of product properties for crude distillation units [J].
Chatterjee, T ;
Saraf, DN .
JOURNAL OF PROCESS CONTROL, 2004, 14 (01) :61-77
[9]   Refinery short-term scheduling with tank farm, inventory and distillation management: An integrated simulation-based approach [J].
Chryssolouris, G ;
Papakostas, N ;
Mourtzis, D .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2005, 166 (03) :812-827
[10]   Design of neural networks using genetic algorithm for on-line property estimation of crude fractionator products [J].
Dam, M ;
Saraf, DN .
COMPUTERS & CHEMICAL ENGINEERING, 2006, 30 (04) :722-729