EconPapers    
Economics at your fingertips  
 

A biofuel-powered study with deep learning neural networks and Dragonfly Algorithm: Optimizing CRDi engine performance with ZnO nanoparticles and cotton seed methyl ester

Manzoore Elahi M. Soudagar, Hua-Rong Wei, Asif Afzal, Vikram Sundara, Yasser Fouad, Fahad Awjah Almehmadi, Sagar Shelare, Shubham Sharma, Teku Kalyani, Yashwant Singh Bisht and Saiful Islam

Energy, 2025, vol. 332, issue C

Abstract: Biodiesel is a non-toxic, carbon-neutral alternative to petroleum diesel that works with existing engines. Wide acceptance is hindered by excessive viscosity, poor cold flow, and weak oxidative stability. Incorporating nanomaterials, such as ZnO nanoparticles, has shown potential in enhancing biodiesel's properties. Previous studies have improved biofuel formulations or engine optimization, but a comprehensive strategy using advanced modeling and optimization techniques is lacking. In the present investigation, the fuel properties were enhanced by addition of ethanol as oxygenated additives and zinc oxide (ZnO) nanoparticles. The engine combustion characters are modelled using deep learning neural networks (DNN) and single-layered neural networks (ANN). Using wider network topology, experimentation with different number of neurons of hidden layer is performed to obtain the optimal coefficient of determination (R-squared). Engine characteristics like brake thermal efficiency (BTE), carbon monoxide (CO), smoke, Hydrocarbon (HC), and ignition delay (ID) are optimized using dragonfly algorithm (DA). Single objective optimization using DA and multi-objective optimization using DA (MODA) is carried out. The DA and MODA are executed for number of cycles and the optimal values and pareto fronts are analyzed. ANN modelling has shown lower in prediction of the engine combustion characters while DNN is a big success. Deep learning models accurately predicted key engine parameters like heat release rate (HRR) and in-cylinder pressure (ICP), achieving R2 > 0.95. The engine emissions are within an acceptable range, and the BTE is within the range of 20 %–32 % as a result of the engine performance optimization. The optimization of engine characteristics is achieved through the incorporation of nanoparticles in biodiesel. This study underscores the potential of combining advanced biofuel formulations, machine learning, and nature-inspired optimization to create eco-friendly and efficient biofuel-powered engines, advancing sustainable energy initiatives.

Keywords: ANN modelling; Biodiesel; Engine; Optimization; Thermal efficiency; Emission (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225026738
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:332:y:2025:i:c:s0360544225026738

DOI: 10.1016/j.energy.2025.137031

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().

 
Page updated 2025-07-15
Handle: RePEc:eee:energy:v:332:y:2025:i:c:s0360544225026738