Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Engineering and Technological Sciences
Rairikar, Sandeep
Unknown Affiliation
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Experimental Investigation and Prediction of Combustion Parameters using Machine Learning in Ethanol - Gasoline Blended Engines Sonawane, Shailesh; Sekhar, Ravi; Warke, Arundhati; Thipse, Sukrut; Rairikar, Sandeep; Varma, Chetan
Journal of Engineering and Technological Sciences Vol. 57 No. 1 (2025): Vol. 57 No. 1 (2025): February
Publisher : Directorate for Research and Community Services, Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/j.eng.technol.sci.2025.57.1.3

Abstract

Alternative fuels play an important role in eco-friendly transport solutions. Wider adoption of alternative blended fuels in automobiles is dependent on a better understanding of the blended fuel engine characteristics. This paper presents an experimental investigation on the part load combustion characteristics of a multi cylinder spark ignition (SI) engine fueled by E0 and E10 ethanol blends. Full factorial Taguchi experimental design was employed to include multi-level engine speed (rpm) and load (throttle %) variations. High-speed data acquisition was used to record combustion parameters viz. maximum pressure (Pmax), indicative mean effective pressure (IMEP), start of combustion (SOC), mass burn fraction (MBF) and burn duration (Brn_drn) over 300 combustion cycles for each experimental run. Grey Relational Analysis (GRA) was used to determine the optimum best and worst engine operating conditions based on Pmax, IMEP, MBF and Brn_drn. Cycle-to-cycle variations of Pmax were also examined in detail to identify the worst engine operating condition. Random Forest machine learning algorithm was employed to accurately model Pmax and SOC in terms of the engine part load operating conditions. This model can be used to predict Pmax and SOC characteristics of an E0/E10 fueled SI engine under different operating conditions, eliminating the need for extensive testing
Co-Authors Sekhar, Ravi Sonawane, Shailesh Thipse, Sukrut Varma, Chetan Warke, Arundhati