Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches
Optimization of biofuel production from algal oil through utilizing a CaO-based catalyst was carried out in this study. The optimal point for the highest yield of the reactions was determined using machine learning. To implement the optimization task, and to make predictions, we used three different...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | Case Studies in Thermal Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214157X23007256 |
_version_ | 1797670304547340288 |
---|---|
author | Jiangbo Tang Ali Kareem Abbas Nisar Ahmad Koka Naiser Sadoon Jamal K. Abbas Rasha Ali Abdalhuseen Munther Abosaooda Naked Mahmood Ahmed Ali Hashim Abbas |
author_facet | Jiangbo Tang Ali Kareem Abbas Nisar Ahmad Koka Naiser Sadoon Jamal K. Abbas Rasha Ali Abdalhuseen Munther Abosaooda Naked Mahmood Ahmed Ali Hashim Abbas |
author_sort | Jiangbo Tang |
collection | DOAJ |
description | Optimization of biofuel production from algal oil through utilizing a CaO-based catalyst was carried out in this study. The optimal point for the highest yield of the reactions was determined using machine learning. To implement the optimization task, and to make predictions, we used three different methods, including Quantile regression, Logistic regression, and Gradient Boosted Decision Trees. The regression problem includes the amount of Catalyst, Reaction time, and Methanol/oil as input features, and FAME (fatty acid methyl ester) yield is the single output. We tuned the boosted version of these models with their important hyper-parameters and selected their best combination. Then different standard metrics are employed to assess their performance of them. Considering R2 score, Quantile regression, Logistic regression, and Gradient Boosted Decision Trees have error rates of 0.934, 0.996, and 0.998, and with MAE, they have 1.94, 1.68, and 1.17 errors, respectively. Also, Considering MAPE 2.14×10-2, 1.89×10-2, and 1.29×10-2 values obtained. Gradient Boosting is selected as the most appropriate model finally. Furthermore, the optimal output value with the proposed approach is 97.50, with the input vector being (x1 = 153, x2 = 0.625, x3 = 20). |
first_indexed | 2024-03-11T20:57:46Z |
format | Article |
id | doaj.art-6f72766a4b934937a37ebc85519e2768 |
institution | Directory Open Access Journal |
issn | 2214-157X |
language | English |
last_indexed | 2024-03-11T20:57:46Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | Case Studies in Thermal Engineering |
spelling | doaj.art-6f72766a4b934937a37ebc85519e27682023-09-30T04:54:37ZengElsevierCase Studies in Thermal Engineering2214-157X2023-10-0150103419Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approachesJiangbo Tang0Ali Kareem Abbas1Nisar Ahmad Koka2Naiser Sadoon3Jamal K. Abbas4Rasha Ali Abdalhuseen5Munther Abosaooda6Naked Mahmood Ahmed7Ali Hashim Abbas8School of Engineering, Guangzhou College of Technology and Business, Foshan, Guangdong, 528100, China; Institute of New Generation Electronic Information Technology, Guangzhou College of Technology and Business, Foshan, Guangdong, 528100, China; Corresponding author. School of Engineering, Guangzhou College of Technology and Business, Foshan, Guangdong, 528100, China.Intelligent Medical Systems Department, Al-Mustaqbal University College, 51001, Hillah, Babil, IraqDepartment of English, Faculty of Languages and Translation, King Khalid University, Abha, Kingdom of Saudi ArabiaMedical Lab. Techniques Department, College of Medical Technology, Al-Farahidi University, IraqAL-Nisour University College, Baghdad, IraqDepartment of Pharmacy, AlNoor University College, Nineveh, IraqCollege of Pharmacy, The Islamic University, 54001, Najaf, IraqNational University of Science and Technology, Dhi Qar, IraqCollege of Information Technology, Imam Ja'afar Al‐Sadiq University, Al‐Muthanna, 66002, IraqOptimization of biofuel production from algal oil through utilizing a CaO-based catalyst was carried out in this study. The optimal point for the highest yield of the reactions was determined using machine learning. To implement the optimization task, and to make predictions, we used three different methods, including Quantile regression, Logistic regression, and Gradient Boosted Decision Trees. The regression problem includes the amount of Catalyst, Reaction time, and Methanol/oil as input features, and FAME (fatty acid methyl ester) yield is the single output. We tuned the boosted version of these models with their important hyper-parameters and selected their best combination. Then different standard metrics are employed to assess their performance of them. Considering R2 score, Quantile regression, Logistic regression, and Gradient Boosted Decision Trees have error rates of 0.934, 0.996, and 0.998, and with MAE, they have 1.94, 1.68, and 1.17 errors, respectively. Also, Considering MAPE 2.14×10-2, 1.89×10-2, and 1.29×10-2 values obtained. Gradient Boosting is selected as the most appropriate model finally. Furthermore, the optimal output value with the proposed approach is 97.50, with the input vector being (x1 = 153, x2 = 0.625, x3 = 20).http://www.sciencedirect.com/science/article/pii/S2214157X23007256BiodieselOptimizationModelingMachine learningEnergy |
spellingShingle | Jiangbo Tang Ali Kareem Abbas Nisar Ahmad Koka Naiser Sadoon Jamal K. Abbas Rasha Ali Abdalhuseen Munther Abosaooda Naked Mahmood Ahmed Ali Hashim Abbas Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches Case Studies in Thermal Engineering Biodiesel Optimization Modeling Machine learning Energy |
title | Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches |
title_full | Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches |
title_fullStr | Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches |
title_full_unstemmed | Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches |
title_short | Optimization of thermal biofuel production from biomass using CaO-based catalyst through different algorithm-based machine learning approaches |
title_sort | optimization of thermal biofuel production from biomass using cao based catalyst through different algorithm based machine learning approaches |
topic | Biodiesel Optimization Modeling Machine learning Energy |
url | http://www.sciencedirect.com/science/article/pii/S2214157X23007256 |
work_keys_str_mv | AT jiangbotang optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT alikareemabbas optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT nisarahmadkoka optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT naisersadoon optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT jamalkabbas optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT rashaaliabdalhuseen optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT muntherabosaooda optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT nakedmahmoodahmed optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches AT alihashimabbas optimizationofthermalbiofuelproductionfrombiomassusingcaobasedcatalystthroughdifferentalgorithmbasedmachinelearningapproaches |