Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization

Lyu, Feng; Yang, Xiaojun; Lyu, Long

Feng Lyu, Xiaojun Yang, Long Lyu

Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization

Abstract:

On the basis of the given material, in order to increase the RON retention of the catalytic cracking unit, the prediction model of gasoline octane retention and the best operation variable inversion model were established based on the Ridge regression model and Gradient descent method. First, based on the Ridge regression model, the leave-one method is used to obtain the relative importance of the operational variables, and select the most important variables, so as to reduce the characteristic dimension of the model; Then, the RON retention prediction model is trained based on the Ridge regression model; Finally, based on the trained Ridge regression model and its weight parameters, the optimal operating variables were optimized separately using the gradient when the operation variable has a range or no range of value. The experimental results show that when 146 are selected from 361 operating variables, the model loss value stabilizes; when α is 0.6, the test set R2 is 0.9882, test set MSE is 0.0193, and the comprehensive performance is better than the random forest, support vector machine model; When the operation variable has two categories of value range and no value range, 2,000 times, the best inversion value of the operation variable makes the RON retention prediction value of the test sample similar to the expected value, and the MAE drops to 2.89999×10-3 and 7.62939×10-6, respectively. In conclusion, the RON retention prediction model proposed in this study has good results, and the best operating variable can be reversed, based on the given material parameters, making the optimal RON retention quantity.

Keywords:
RON retention prediction; Ridge regression model; Leave-One-Out; Gradient descent algorithm; inversion; machine learning

Issue: 2024, Volume 75, Issue 1

Pages: 12-32

Publication date: 2024/2/1

https://doi.org/10.37358/RC.24.1.8580

Download Pdf Article

This article is published under the Creative Commons Attribution 4.0 International License

Citation Styles

Cite this article as:
LYU, F., YANG, X., LYU, L., Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization, Rev. Chim., 75(1), 2024, 12-32.

Vancouver
Lyu F, Yang X, Lyu L. Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization. Rev. Chim.[internet]. 2024 Jan;75(1):12-32. Available from: https://doi.org/10.37358/RC.24.1.8580

APA 6th edition
Lyu, F., Yang, X. & Lyu, L. (2024). Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization. Revista de Chimie, 75(1), 12-32. https://doi.org/10.37358/RC.24.1.8580

Harvard
Lyu, F., Yang, X., Lyu, L. (2024). 'Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization', Revista de Chimie, 75(1), pp. 12-32. https://doi.org/10.37358/RC.24.1.8580

IEEE
F. Lyu, X. Yang, L. Lyu, "Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization". Revista de Chimie, vol. 75, no. 1, pp. 12-32, 2024. [online]. https://doi.org/10.37358/RC.24.1.8580

Text
Feng Lyu, Xiaojun Yang, Long Lyu,
Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization,
Revista de Chimie,
Volume 75, Issue 1,
2024,
Pages 12-32,
ISSN 2668-8212,
https://doi.org/10.37358/RC.24.1.8580.
(https://revistadechimie.ro/Articles.asp?ID=8580)
Keywords: RON retention prediction; Ridge regression model; Leave-One-Out; Gradient descent algorithm; inversion; machine learning

RIS
TY - JOUR
T1 - Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization
A1 - Lyu, Feng
A2 - Yang, Xiaojun
A3 - Lyu, Long
JF - Revista de Chimie
JO - Rev. Chim.
PB - Revista de Chimie SRL
SN - 2668-8212
Y1 - 2024
VL - 75
IS - 1
SP - 12
EP - 32
UR - https://doi.org/10.37358/RC.24.1.8580
KW - RON retention prediction
KW - Ridge regression model
KW - Leave-One-Out
KW - Gradient descent algorithm
KW - inversion
KW - machine learning
ER -

BibTex
@article{RevCh2024P12,
author = {Lyu Feng and Yang Xiaojun and Lyu Long},
title = {Analysis of Octane Retention Prediction Model for Catalytic Cracked Gasoline Based on Ridge Regression Model and Gradient Descent Optimization},
journal = {Revista de Chimie},
volume = {75},
number = {1},
pages = {12-32},
year = {2024},
issn = {2668-8212},
doi = {https://doi.org/10.37358/RC.24.1.8580},
url = {https://revistadechimie.ro/Articles.asp?ID=8580}
}

Download article Citations:

PUBLISHING SECTION

Author Guidelines

* Paper Drafting

* Paper Template

* Ethical Statement

* Paper Submission

Ghidul Autorului (ro)

Open Access & Archiving Policy

Search Authors

LATEST NEWS
	NUMAR OMAGIAL PETRU PONI.. detalii
	Revista de Chimie - 70 de ani de aparitie neintrerupta.. detalii
	English-Romanian Dictionary for Mechanical Engineering (download pdf)