Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization

This study presents the design and optimization of a biodiesel production process, emphasizing the integration of machine learning (ML) models and process optimization techniques. The biodiesel production process involves multiple stages, including feedstock preparation, esterification, and transest...

Full description

Saved in:
Bibliographic Details
Main Authors: Badril Azhar, Muhammad Ikhsan Taipabu, Cries Avian, Karthickeyan Viswanathan, Wei Wu, Raymond Lau
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:Energy Conversion and Management: X
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590174525001321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725510030983168
author Badril Azhar
Muhammad Ikhsan Taipabu
Cries Avian
Karthickeyan Viswanathan
Wei Wu
Raymond Lau
author_facet Badril Azhar
Muhammad Ikhsan Taipabu
Cries Avian
Karthickeyan Viswanathan
Wei Wu
Raymond Lau
author_sort Badril Azhar
collection DOAJ
description This study presents the design and optimization of a biodiesel production process, emphasizing the integration of machine learning (ML) models and process optimization techniques. The biodiesel production process involves multiple stages, including feedstock preparation, esterification, and transesterification, with catalysts Amberlyst-15 and KOH used in continuous stirred-tank reactors (CSTRs). Sensitivity analysis reveals that high conversions of free fatty acids (94 %) and triglycerides (97 %) are achievable under optimized operating conditions. To enhance process efficiency, adjustments to reaction temperature, time, and methanol-to-oil ratios are proposed, resulting in lower energy consumption and material costs. A ML model evaluation, using various algorithms, identify XGBoost, Extra Trees, Gradient Boosting, LGBM, and Random Forest demonstrate the best performer for predicting process parameters, achieving an R2 value of nearly to 1. Particle Swarm Optimization (PSO) is then employed to optimize the selected ML model (XGBoost), leading to the identification of optimal input parameters for biodiesel production. The optimized process, combined with heat integration, reduces pre-heating energy requirements by 80.9 % and total heat duties by 19.9 %. The findings demonstrate the effectiveness of combining ML and optimization techniques to enhance biodiesel production efficiency while reducing costs and energy consumption.
format Article
id doaj-art-e93332f749904a9b82ac90c8a3b120e7
institution DOAJ
issn 2590-1745
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series Energy Conversion and Management: X
spelling doaj-art-e93332f749904a9b82ac90c8a3b120e72025-08-20T03:10:27ZengElsevierEnergy Conversion and Management: X2590-17452025-04-012610100010.1016/j.ecmx.2025.101000Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimizationBadril Azhar0Muhammad Ikhsan Taipabu1Cries Avian2Karthickeyan Viswanathan3Wei Wu4Raymond Lau5Department of Chemical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya 60111, IndonesiaDepartment of Chemical Engineering, Pattimura University, Ambon 97134, IndonesiaDepartement of Electrical Engineering, Brawijaya University, IndonesiaDepartment of Mechanical Engineering, Dr. N.G.P. Institute of Technology, Coimbatore 641048, IndiaDepartment of Chemical Engineering, National Cheng Kung University, Tainan 70101, Taiwan; Academy of Innovative Semiconductor and Sustainable Manufacturing, National Cheng Kung University, Tainan 70101, Taiwan; Corresponding author.School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, 62 Nanyang Drive, Singapore 637459 SingaporeThis study presents the design and optimization of a biodiesel production process, emphasizing the integration of machine learning (ML) models and process optimization techniques. The biodiesel production process involves multiple stages, including feedstock preparation, esterification, and transesterification, with catalysts Amberlyst-15 and KOH used in continuous stirred-tank reactors (CSTRs). Sensitivity analysis reveals that high conversions of free fatty acids (94 %) and triglycerides (97 %) are achievable under optimized operating conditions. To enhance process efficiency, adjustments to reaction temperature, time, and methanol-to-oil ratios are proposed, resulting in lower energy consumption and material costs. A ML model evaluation, using various algorithms, identify XGBoost, Extra Trees, Gradient Boosting, LGBM, and Random Forest demonstrate the best performer for predicting process parameters, achieving an R2 value of nearly to 1. Particle Swarm Optimization (PSO) is then employed to optimize the selected ML model (XGBoost), leading to the identification of optimal input parameters for biodiesel production. The optimized process, combined with heat integration, reduces pre-heating energy requirements by 80.9 % and total heat duties by 19.9 %. The findings demonstrate the effectiveness of combining ML and optimization techniques to enhance biodiesel production efficiency while reducing costs and energy consumption.http://www.sciencedirect.com/science/article/pii/S2590174525001321Artificial intelligenceBiodiesel ProductionMachine learningParticle Swarm Optimization
spellingShingle Badril Azhar
Muhammad Ikhsan Taipabu
Cries Avian
Karthickeyan Viswanathan
Wei Wu
Raymond Lau
Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
Energy Conversion and Management: X
Artificial intelligence
Biodiesel Production
Machine learning
Particle Swarm Optimization
title Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
title_full Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
title_fullStr Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
title_full_unstemmed Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
title_short Artificial intelligence-driven modeling of biodiesel production from fats, oils, and grease (FOG) with process optimization via particle swarm optimization
title_sort artificial intelligence driven modeling of biodiesel production from fats oils and grease fog with process optimization via particle swarm optimization
topic Artificial intelligence
Biodiesel Production
Machine learning
Particle Swarm Optimization
url http://www.sciencedirect.com/science/article/pii/S2590174525001321
work_keys_str_mv AT badrilazhar artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization
AT muhammadikhsantaipabu artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization
AT criesavian artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization
AT karthickeyanviswanathan artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization
AT weiwu artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization
AT raymondlau artificialintelligencedrivenmodelingofbiodieselproductionfromfatsoilsandgreasefogwithprocessoptimizationviaparticleswarmoptimization