Research Papers: Thermal Systems

Modeling of Thermal Cracking Furnaces Via Exergy Analysis Using Hybrid Artificial Neural Network–Genetic Algorithm

[+] Author and Article Information
M. Alizadeh

Chemical Engineering Department,
Tarbiat Modares University,
Tehran 14115-114, Iran

S. M. Sadrameli

Chemical Engineering Department,
Tarbiat Modares University,
Tehran 14115-114, Iran
e-mail: sadramel@modares.ac.ir

1Corresponding author.

Contributed by the Heat Transfer Division of ASME for publication in the JOURNAL OF HEAT TRANSFER. Manuscript received December 17, 2014; final manuscript received December 1, 2015; published online January 20, 2016. Assoc. Editor: Antonio Barletta.

J. Heat Transfer 138(4), 042801 (Jan 20, 2016) (11 pages) Paper No: HT-14-1819; doi: 10.1115/1.4032171 History: Received December 17, 2014; Revised December 01, 2015

In this study, we try to make an exergy analysis of an olefin cracking furnace more understandable by coupling it with the use of an artificial neural network–generic algorithm (ANN–GA) modeling. The presented method permits to provide an energy diagnosis of the process under a wide range of operating conditions. As a case study, one of the petrochemical complexes in Iran has been considered. The Petrosim process simulator software was used to obtain thermodynamic properties of the process streams and to perform exergy balances. The results are validated with industrial data obtained from the plant. The exergy destruction and exergetic efficiency for the main system components and the entire system were calculated. The simulation results reveal that the exergetic loss of the process increases with increasing steam ratio (SR) and decreases with coil outlet temperature (COT) and residence time (RT). The results show that the overall exergetic efficiency of the system is about 65%. The recorded and calculated data have been used as inputs for the neural network. The results show that ANN–GA is a highly effective method to optimize the performance of the neural networks, predicting the overall exergy efficiency. Comparing to phenomenological modeling based on the detailed knowledge of the furnace condition, the use of the introduced ANN–GA model saves significant amount of the time needed for the performance prediction of cracking furnaces.

Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Integrated heating system in a thermal cracking furnace of an olefin plant

Grahic Jump Location
Fig. 3

Typical architecture of a feed forward BP neural network

Grahic Jump Location
Fig. 2

Grassmann representation of a process or system

Grahic Jump Location
Fig. 4

Framework of the ANN–GA method

Grahic Jump Location
Fig. 5

Schematic diagram of the cracking furnace for the considered petrochemical Co

Grahic Jump Location
Fig. 9

Effect of RT on furnace exergetic efficiency

Grahic Jump Location
Fig. 6

Exergy efficiency of convection section banks

Grahic Jump Location
Fig. 7

Process fluid and flue gas temperature along the convection section

Grahic Jump Location
Fig. 8

Effect of SR on furnace exergetic efficiency

Grahic Jump Location
Fig. 10

Scatter diagram for exergetic efficiency based on ANN–GA approach in terms of correlation coefficient (R2)

Grahic Jump Location
Fig. 11

The comparison between ANN–GA outcomes and real values of exergetic efficiency for all data

Grahic Jump Location
Fig. 12

Relative error of the determined exergetic efficiency values of the GA–ANN model from real values




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In