Scholarly record
ARTIFICIAL NEURAL NETWORK VS. LINEAR REGRESSION FOR MODELING REACTOR OF THE CATALYTIC CRACKING PROCESS
Abstract
The paper presents the research and results obtained by authors concerning the reactor modeling of the catalytic cracking process using two methods: artificial neural network (ANN) and multiple linear regression (MLR). This study is structured in four parts. The first part presents the process description, and the existing models in the literature. The second part presents the multiple linear regression method, the reactor model obtained with this method, and the comparison between the output experimental data of the reactor and output variables predicted with the MLR method. The experimental data were taken from a Romanian refinery. The next section describes the steps involved to build the neural network developed by authors for modeling the reactor, and the result of the comparison between the output experimental data of the reactor and output variables predicted with the ANN. The result shows that the neural model developed for the reactor is superior to the statistical model obtained with multiple linear regression.
Publication Impact Profile
- Citations
- CrossRef - Citation Indexes: 1
- Scopus - Citation Indexes: 0
- Captures
- Mendeley - Readers: 1
Publication details
References14
Popa C., Patra?cioiu C., Approach in Modelling, Simulation and Hierarchical Control of the Fluid Catalytic Cracking Process I - Process Modeling, vol. 61, 2010, pp. 419-426.
Reza S., Fluid Catalytic Cracking Handbook Design, Operating and Troubleshooting of FCC Facilities, Gulf Publishing Company, Houston Texas, 2000.
Michalopouls J., Papapdokonstadakis S. AramPatzis G., Lygeros A., Modelling an industrial fluid catalytic cracking unit using neural networks, Tans I Chem E., vol 79 Part A, 2001, pp. 137-143. DOI: 10.1205/02638760151095944
Mustapha K, K, Mujahed A. D., Othman T., Artificial intelligence perspectives: A systematic literature review on modeling, control and optimization of fluid catalytic cracking, Alexandria Engineering Journal, vol. 80, 2023, pp 295-314. DOI: 10.1016/j.aej.2023.08.066
Al- Enezi G., Fawzi N., Elkamel A., Development of regression models to control product yields and properties of fluid catalytic cracking process, Petroleum Scinec technology, vol. 17, 1999, pp. 535-552. DOI: 10.1080/10916469908949733
Yang F., Zhaiu M., Dai C. N., Cao J., Construction, and analysis of gasoline yield prediction model for FCCC unit based on artificial intelligence algorithm, Acta Petrolei Sinica, vol. 35, 2019, pp 807-817.
Bollas G.M., Papapdokinstadakis S., Mivhalopoulos J., Arampatiz G., Lygeros A., Using hybrid neural networks in scaling an FCC model from pilot plant to an industrial unit, Chemical Engineering Process, vol 42, 2003, pp. 697-713. DOI: 10.1016/s0255-2701(02)00206-4
Yang F., Dai C., Tang J., Jin X., Cao J., A hybrid deep learning and mechanistic kinetics model for a prediction of fluid catalytic cracking performance, Chemical Engineering Research and Desing, vol. 15, 2020, pp 202-220. DOI: 10.1016/j.cherd.2020.01.013
Maulud D. H., Abdulazeez A. M, A Review on Linear Regression Comprehensive in Machine Learning, Journal of Applied Science and Technology Trends, vol. 1, 2010, pp. 140 �147. DOI: 10.38094/jastt1457
Mechelli A, Vieira S., Machine Learning: Methods and Applications to Brain Disorders, Elsevier, 2019.
Tosun E., Aydin K, Bilgili M., Comparison of linear regression and artificial neural network model of a diesel engine fueled with biodiesel-alcohol mixtures, Alexandria Engineering Journal, vol. 55, 2016, pp. 3081-3089. DOI: 10.1016/j.aej.2016.08.011
Carbureanu M., Mihalache S. F., Zamfir F., Machine Learning Methods Applied for Wastewater pH Neutralization Process Modeling, 2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Ploiesti, Romania, 2022, pp. 1-6. DOI: 10.1109/ecai54874.2022.9847479
Haykin S., Neural Networks: A Comprehensive Foundation, Pentice Hall, Ontario, 1999.
Sinsomboonthon S., Performance Comparison of New Adjusted Min-Max with Decimal Scaling and Statistical Column Normalization Methods for Artificial Neural Network Classification, International Journal of Mathematics and Mathematical Sciences, vol. 6, 2022, pp. 2-11. DOI: 10.1155/2022/3584406
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.