Citation

Al Awadh, Mohammed and Goh, Michael Kang Ong (2026) Response surface and TQM-ML analysis of a PCCI engine fueled with PO and microalgae biodiesel. Scientific Reports, 16 (1). ISSN 2045-2322

Text s41598-026-40929-1.pdf - Published Version Restricted to Repository staff only Download (20MB)

Abstract

This work presents a comprehensive experimental and data-driven study on the feasibility of pine-oil-aided premixed charge compression ignition (PCCI) combustion under low-temperature combustion (LTC) conditions in a variable compression ratio (VCR) diesel engine using conventional diesel and biodiesel blends to operate as pilot fuel. Different amounts of Pine Oil (PO) were used at 16, 17.5, and 19 compression ratios with different engine loads during tests. Performance and emissions results such as BTE, BSFC, CO, HC, NOx, and smoke opacity were examined. RSM generated statistically significant quadratic models and was used for simultaneous multi-objective optimisation. The optimal operating condition is CR = 19 with 30% PO with 80% load. This yielded a peak BTE of 35.4%, a minimum BSFC of 0.25 kg/kWh, a CO level of 0.022%, an HC level of 31 ppm and a smoke opacity of 21 HSU. NOx: an increase (1120 ppm) was also observed. In the present work, nine regression models were employed in a framework for machine learning. Among various models, the Gradient Boosting Machine had the highest prediction accuracy (R2 > 0.95). SHAP-based explainable AI revealed that engine load, compression ratio, and fuel properties were the most influential on how combustion behaved. The TQM and sustainability assessment based on the Pugh matrix indicated that the use of PO to enable operating PCCI at higher compression ratios offers the best compromise of efficiency with low emissions and sustainability between the different options. These combined outcomes indicate that PO has significant potential as a renewable fuel for advanced low-carbon compression ignition engines.

Item Type:	Article
Uncontrolled Keywords:	PCCI combustion, PO, Variable compression ratio engine, Response surface methodology, Machine learning, SHAP analysis, Total quality management, Pugh matrix, Sustainability assessment, Emission characteristics
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	04 May 2026 02:48
Last Modified:	04 May 2026 02:48
URII:	http://shdl.mmu.edu.my/id/eprint/15833

Downloads

Edit (login required)