Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties

Biodiesel is assumed a renewable and environmentally friendly fuel that possesses the potential to substitute petroleum diesel. The basic purpose of the present study is to design a precise algorithm based on Gaussian Process Regression (GPR) model with several kernel functions, i.e., Rational Quadr...

Full description

Saved in:
Bibliographic Details
Main Authors: Inna Pustokhina, Amir Seraj, Hafsan Hafsan, Seyed Mojtaba Mostafavi, S. M. Alizadeh
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:International Journal of Chemical Engineering
Online Access:http://dx.doi.org/10.1155/2021/5650499
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832561178572750848
author Inna Pustokhina
Amir Seraj
Hafsan Hafsan
Seyed Mojtaba Mostafavi
S. M. Alizadeh
author_facet Inna Pustokhina
Amir Seraj
Hafsan Hafsan
Seyed Mojtaba Mostafavi
S. M. Alizadeh
author_sort Inna Pustokhina
collection DOAJ
description Biodiesel is assumed a renewable and environmentally friendly fuel that possesses the potential to substitute petroleum diesel. The basic purpose of the present study is to design a precise algorithm based on Gaussian Process Regression (GPR) model with several kernel functions, i.e., Rational Quadratic, Squared Exponential, Matern, and Exponential, to estimate biodiesel properties. These properties include kinematic viscosity (KV), pour point (PP), iodine value (IV), and cloud point (CP) as a function of fatty acid composition. In order to develop this model, some variables are assumed, such as molecular weight, carbon number, double bond numbers, monounsaturated fatty acids, polyunsaturated fatty acid, weight percent of saturated acid, and temperature. The performance and efficiency of the GPR model are measured through several statistical criteria and the results are summarized in root mean square error (RMSE) and coefficients of determination (R2). R2 and RMSE are sorted as 0.992 & 0.15697, 0.998 & 0.96580, 0.966 & 1.38659, and 0.968 & 1.56068 for four properties such as KV, IV, CP, and PP, respectively. It is worth to mention this point that the kernel function Squared Exponential shows a great performance for IV and PP and kernel functions Exponential and Matern indicate appropriate efficiency for CP and KV properties, respectively. On the other hand, the results of the offered GPR models are compared with those of the previous models, LSSVM-PSO and ANFIS. The outcomes proved the superiority of this model over two former models in point of estimating the biodiesel properties.
format Article
id doaj-art-ce55e0aaaa994e56989d947c0266798a
institution Kabale University
issn 1687-806X
1687-8078
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series International Journal of Chemical Engineering
spelling doaj-art-ce55e0aaaa994e56989d947c0266798a2025-02-03T01:25:48ZengWileyInternational Journal of Chemical Engineering1687-806X1687-80782021-01-01202110.1155/2021/56504995650499Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel PropertiesInna Pustokhina0Amir Seraj1Hafsan Hafsan2Seyed Mojtaba Mostafavi3S. M. Alizadeh4Department of Propaedeutics of Dental Diseases, I. M. Sechenov First Moscow State Medical University, Sechenov University, Moscow, RussiaDepartment of Instrumentation and Industrial Automation, Ahwaz Faculty of Petroleum Engineering, Petroleum University of Technology (PUT), Ahwaz, IranBiology Department, Faculty of Science and Technology, Universitas Islam Negeri Alauddin Makassar, Sultan Alauddin Street, Gowa 92118, South Sulawesi, IndonesiaHiTech Institute of Theoretical and Computational Chemistry, IndiaPetroleum Engineering Department, Australian College of Kuwait, West Mishref, Kuwait City, KuwaitBiodiesel is assumed a renewable and environmentally friendly fuel that possesses the potential to substitute petroleum diesel. The basic purpose of the present study is to design a precise algorithm based on Gaussian Process Regression (GPR) model with several kernel functions, i.e., Rational Quadratic, Squared Exponential, Matern, and Exponential, to estimate biodiesel properties. These properties include kinematic viscosity (KV), pour point (PP), iodine value (IV), and cloud point (CP) as a function of fatty acid composition. In order to develop this model, some variables are assumed, such as molecular weight, carbon number, double bond numbers, monounsaturated fatty acids, polyunsaturated fatty acid, weight percent of saturated acid, and temperature. The performance and efficiency of the GPR model are measured through several statistical criteria and the results are summarized in root mean square error (RMSE) and coefficients of determination (R2). R2 and RMSE are sorted as 0.992 & 0.15697, 0.998 & 0.96580, 0.966 & 1.38659, and 0.968 & 1.56068 for four properties such as KV, IV, CP, and PP, respectively. It is worth to mention this point that the kernel function Squared Exponential shows a great performance for IV and PP and kernel functions Exponential and Matern indicate appropriate efficiency for CP and KV properties, respectively. On the other hand, the results of the offered GPR models are compared with those of the previous models, LSSVM-PSO and ANFIS. The outcomes proved the superiority of this model over two former models in point of estimating the biodiesel properties.http://dx.doi.org/10.1155/2021/5650499
spellingShingle Inna Pustokhina
Amir Seraj
Hafsan Hafsan
Seyed Mojtaba Mostafavi
S. M. Alizadeh
Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
International Journal of Chemical Engineering
title Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
title_full Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
title_fullStr Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
title_full_unstemmed Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
title_short Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
title_sort developing a robust model based on the gaussian process regression approach to predict biodiesel properties
url http://dx.doi.org/10.1155/2021/5650499
work_keys_str_mv AT innapustokhina developingarobustmodelbasedonthegaussianprocessregressionapproachtopredictbiodieselproperties
AT amirseraj developingarobustmodelbasedonthegaussianprocessregressionapproachtopredictbiodieselproperties
AT hafsanhafsan developingarobustmodelbasedonthegaussianprocessregressionapproachtopredictbiodieselproperties
AT seyedmojtabamostafavi developingarobustmodelbasedonthegaussianprocessregressionapproachtopredictbiodieselproperties
AT smalizadeh developingarobustmodelbasedonthegaussianprocessregressionapproachtopredictbiodieselproperties