A Deep Learning Framework in FCC Process Control
Lists
Only you see this
Abstract
The controlling of exhaust gas from gasoline is crucial for atmospheric environment protection. Research Octane Number (RON) loss and restricted sulphur (S) content matter the quality of gasoline. To obtain gasoline with high quality, the paper proposes a novel data-driven optimization model integrating deep neural network (DNN) and genetic algorithm (GA) to model for Fluid Catalytic Cracking (FCC) process then optimize. To begin with, the DNN is used to fit the relations between 13 related input variables and output variables in FCC. Subsequently, the FCC process is modelled and GA is proposed to solve the optimization model. Ultimately, 305 samples from real datasets have been analysed to testify feasibility and effectiveness of the method. This paper provides a guideline for the production process of FCC gasoline.
BibTeX
@inproceedings{yan2021deep,
author = {Qiuna Yan and Xiaola Lin and Zhan Qin and Gan Luo and D Q Wang and Xueli Xiao},
title = {{A Deep Learning Framework in FCC Process Control}},
booktitle = {Advances},
year = {2021},
doi = {10.3233/atde210342},
}Loading related content...