Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks

M. V. Cristea; R. Roman; P. S. Agachi

Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks

M. V. Cristea, R. Roman, P. S. Agachi

Chemical, Materials & Metallurgical Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

The dynamic behavior of the FCC unit was simulated using artificial neural networks (ANN). An analytical model, validated with construction and operation data, was used for producing a comprehensive input-target set of training data. The model predicted the final production rate of the main products, gasoline and diesel. The architecture and training algorithm used by the ANN were efficient and this was proved by the results obtained both on training set and set of input-target data not met during the training procedure. The same good ANN performance was obtained by the comparison between dynamic simulations results emerged from the ANN vs. first principle modeling, both using the same randomly varying inputs. The computation time was reduced when using the ANN model, compared to the use of the analytical model. This is an abstract of a paper presented at the 18th International Congress of Chemical Process Engineering (Praque, Czech Republic 8/24-28/2008).

Original language	English
Publication status	Published - 2008
Event	18th International Congress of Chemical and Process Engineering, CHISA 2008 - Prague, Czech Republic Duration: Aug 24 2008 → Aug 28 2008

Other

Other	18th International Congress of Chemical and Process Engineering, CHISA 2008
Country	Czech Republic
City	Prague
Period	8/24/08 → 8/28/08

All Science Journal Classification (ASJC) codes

Chemical Engineering (miscellaneous)
Process Chemistry and Technology

Access to Document

Fingerprint Dive into the research topics of 'Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks'. Together they form a unique fingerprint.

Cite this

@conference{56d4d297f2e54109bb7c54780516b2ff,

title = "Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks",

abstract = "The dynamic behavior of the FCC unit was simulated using artificial neural networks (ANN). An analytical model, validated with construction and operation data, was used for producing a comprehensive input-target set of training data. The model predicted the final production rate of the main products, gasoline and diesel. The architecture and training algorithm used by the ANN were efficient and this was proved by the results obtained both on training set and set of input-target data not met during the training procedure. The same good ANN performance was obtained by the comparison between dynamic simulations results emerged from the ANN vs. first principle modeling, both using the same randomly varying inputs. The computation time was reduced when using the ANN model, compared to the use of the analytical model. This is an abstract of a paper presented at the 18th International Congress of Chemical Process Engineering (Praque, Czech Republic 8/24-28/2008).",

author = "Cristea, {M. V.} and R. Roman and Agachi, {P. S.}",

year = "2008",

language = "English",

note = "18th International Congress of Chemical and Process Engineering, CHISA 2008 ; Conference date: 24-08-2008 Through 28-08-2008",

}

TY - CONF

T1 - Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks

AU - Cristea, M. V.

AU - Roman, R.

AU - Agachi, P. S.

PY - 2008

Y1 - 2008

N2 - The dynamic behavior of the FCC unit was simulated using artificial neural networks (ANN). An analytical model, validated with construction and operation data, was used for producing a comprehensive input-target set of training data. The model predicted the final production rate of the main products, gasoline and diesel. The architecture and training algorithm used by the ANN were efficient and this was proved by the results obtained both on training set and set of input-target data not met during the training procedure. The same good ANN performance was obtained by the comparison between dynamic simulations results emerged from the ANN vs. first principle modeling, both using the same randomly varying inputs. The computation time was reduced when using the ANN model, compared to the use of the analytical model. This is an abstract of a paper presented at the 18th International Congress of Chemical Process Engineering (Praque, Czech Republic 8/24-28/2008).

AB - The dynamic behavior of the FCC unit was simulated using artificial neural networks (ANN). An analytical model, validated with construction and operation data, was used for producing a comprehensive input-target set of training data. The model predicted the final production rate of the main products, gasoline and diesel. The architecture and training algorithm used by the ANN were efficient and this was proved by the results obtained both on training set and set of input-target data not met during the training procedure. The same good ANN performance was obtained by the comparison between dynamic simulations results emerged from the ANN vs. first principle modeling, both using the same randomly varying inputs. The computation time was reduced when using the ANN model, compared to the use of the analytical model. This is an abstract of a paper presented at the 18th International Congress of Chemical Process Engineering (Praque, Czech Republic 8/24-28/2008).

UR - http://www.scopus.com/inward/record.url?scp=84867593488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867593488&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84867593488

T2 - 18th International Congress of Chemical and Process Engineering, CHISA 2008

Y2 - 24 August 2008 through 28 August 2008

ER -