Deep learning economic model predictive control for refinery operation: A fluid catalytic cracker - fractionator case study

Abstract

An integrated deep learning - economic model predictive control (EMPC) framework for large scale processes is presented. The framework is successfully implemented to a realistic fluid catalytic cracker (FCC) - fractionator process. Scenarios under the effect of no disturbances (nominal) and with disturbances are simulated demonstrating fast computation (potentially allowing industrial implementation) and improved performance (taking into account process nonlinear behavior, enhancing the process operating profit).