Artificial Intelligence for Hybrid Modeling in Fluid Catalytic Cracking (FCC)
Open Access
Abstract
This study reports a novel hybrid model for the prediction of six critical process variables of importance in an industrial-scale FCC (fluid catalytic cracking) riser reactor: vacuum gas oil (VGO) conversion, outlet riser temperature, light cycle oil (LCO), gasoline, light gases, and coke yields. The proposed model is developed via the integration of a computational particle-fluid dynamics (CPFD) methodology with artificial intelligence (AI). The adopted methodology solves the first principle model (FPM) equations numerically using the CPFD Barracuda Virtual Reactor 22.0® software. Based on 216 of these CPFD simulations, the performance of an industrial-scale FCC riser reactor unit was assessed using VGO catalytic cracking kinetics developed at CREC-UWO. The dataset obtained with CPFD is employed for the training and testing of a machine learning (ML) algorithm. This algorithm is based on a multiple output feedforward neural network (FNN) selected to allow one to establish correlations between the riser reactor feeding conditions and its outcoming parameters, with a 0.83 averaged regression coefficient and an overall RMSE of 1.93 being obtained. This research underscores the value of integrating CPFD simulations with ML to optimize industrial processes and enhance their predictive accuracy, offering significant advancements in FCC riser reactor unit operations.Keywords
Funding Information
- Natural Sciences and Engineering Research Council
- Imperial Oil
This publication has 41 references indexed in Scilit:
- Kinetic Modeling of Catalytic Cracking of Gas Oil Feedstocks: Reaction and Diffusion PhenomenaIndustrial & Engineering Chemistry Research, 2006
- Modeling and Simulation of an Industrial Fluid Catalytic Cracking Riser Reactor Using a Lump-Kinetic Model for a Distinct FeedstockIndustrial & Engineering Chemistry Research, 2005
- Simulation of FCC riser flow with multiphase heat transfer and cracking reactionsComputational Mechanics, 2003
- Using hybrid neural networks in scaling up an FCC model from a pilot plant to an industrial unitChemical Engineering and Processing - Process Intensification, 2003
- An Incompressible Three-Dimensional Multiphase Particle-in-Cell Model for Dense Particle FlowsJournal of Computational Physics, 2001
- Dynamic modeling and simulation of a fluidized catalytic cracking process. Part I: Process modelingChemical Engineering Science, 2001
- Neural network based fault diagnosis using unmeasurable inputsEngineering Applications of Artificial Intelligence, 2000
- Modelling FCC units under steady and unsteady state conditionsThe Canadian Journal of Chemical Engineering, 2000
- Dynamic and Control of Fluidized Catalytic Crackers. 1. Modeling of the Current Generation of FCC'sIndustrial & Engineering Chemistry Research, 1995
- Bioprocess optimization and control: Application of hybrid modellingJournal of Biotechnology, 1994