EconPapers    
Economics at your fingertips  
 

Machine Learning Prediction and Optimization of Performance and Emissions Characteristics of IC Engine

Mallesh B. Sanjeevannavar, Nagaraj R. Banapurmath (nrbanapurmath@gmail.com), V. Dananjaya Kumar, Ashok M. Sajjan, Irfan Anjum Badruddin, Chandramouli Vadlamudi, Sanjay Krishnappa, Sarfaraz Kamangar, Rahmath Ulla Baig and T. M. Yunus Khan
Additional contact information
Mallesh B. Sanjeevannavar: Department of Mechanical Engineering, KLE Dr. M S Sheshgiri College of Engineering and Technology, Belagavi 590008, India
Nagaraj R. Banapurmath: Centre of Excellence in Material Science, Department of Mechanical Engineering, KLE Technological University, Hubballi 580031, India
V. Dananjaya Kumar: Department of Aeronautical Engineering, Karavali Institute of Technology, Mangalore 575029, India
Ashok M. Sajjan: Centre of Excellence in Material Science, Department of Mechanical Engineering, KLE Technological University, Hubballi 580031, India
Irfan Anjum Badruddin: Mechanical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia
Chandramouli Vadlamudi: Aerospace Integration Engineer, Aerosapien Technologies, Daytona Beach, FL 32114, USA
Sanjay Krishnappa: Aerospace Integration Engineer, Aerosapien Technologies, Daytona Beach, FL 32114, USA
Sarfaraz Kamangar: Mechanical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia
Rahmath Ulla Baig: Industrial Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia
T. M. Yunus Khan: Mechanical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia

Sustainability, 2023, vol. 15, issue 18, 1-30

Abstract: In this work, a study was conducted to investigate the effects of different biodiesel blends with hydrogen peroxide additive on the performance and emissions of an internal combustion engine under various operating parameters. A CI engine was operated with diesel, four dissimilar biodiesels, and H 2 O 2 at various proportions. The biodiesel blends used were Jatropha (D60JB30A10, D60JB34A6, D60JB38A2, D60JB40), Honge (D60HB30A10, D60HB34A6, D60HB38A2, D60HB40), Simarouba (D60SB30A10, D60SB34A6, D60SB38A2, D60SB40), and Neem (D60NB30A10, D60NB34A6, D60NB38A2, D60NB40). The engine was tested at different injection operating pressures (200, 205, and 210 bar), a speed of 1500 rpm, and a CR of 17.5:1. From the experiments conducted, it was highlighted that, under specific conditions, i.e., with an injection pressure of 205 bar, 80% load, a compression ratio of 17.5, an injection timing set at 230 before top dead center, and an engine speed of 1500 rpm, the biodiesel blends D60JB30A10, D60HB30A10, D60SB30A10, and D60NB30A10 achieved the highest brake thermal efficiencies of 24%, 23.9675%, 23.935%, and 23.9025%, respectively. Notably, the blend D60JB30A10 stood out with the highest brake thermal efficiency of 24% among these tested blends. Similarly, when evaluating emissions under the same operational conditions, the D60JB30A10 blend exhibited the lowest emissions levels: CO (0.16% Vol), CO 2 (7.8% Vol), HC (59 PPM), and Smoke (60 HSU), while NOx (720 PPM) emissions showed a relative increase with higher concentrations of the hydrogen-based additive. The D60HB30A10, D60SB30A10, and D60NB30A10 blends showed higher emissions in comparison. Additionally, the study suggests that machine learning techniques can be employed to predict engine performance and emission characteristics, thereby cutting down on time and costs associated with traditional engine trials. Specifically, machine learning methods, like XG Boost, random forest regressor, decision tree regressor, and linear regression, were utilized for prediction purposes. Among these techniques, the XG Boost model demonstrated highly accurate predictions, followed by the random forest regressor, decision tree regressor, and linear regression models. The accuracy of the predictions for XG Boost model was assessed through evaluation metrics such as R2-Score (0.999), Root Mean Squared Error (0.540), Mean Squared Error (0.248), and Mean Absolute Error (0.292), which allowed for a thorough analysis of the algorithm’s performance compared to actual values.

Keywords: biodiesel; hydrogen peroxide; machine learning models; brake thermal efficiency; evaluation matrices (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/18/13825/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/18/13825/ (text/html)

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:gam:jsusta:v:15:y:2023:i:18:p:13825-:d:1241462

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager (indexing@mdpi.com).

 
Page updated 2024-12-28
Handle: RePEc:gam:jsusta:v:15:y:2023:i:18:p:13825-:d:1241462