Production of biodiesel from Spent Earth Palm Oil and machine learning-based characterisation of ternary blends

Spent earth palm oil (SEPO), a high FFA (32.85%) palm refining waste, was converted to biodiesel in steps: a two acid esterification brought the acid value below 2 mg KOH/g, and base-catalysed transesterification yielded 95% conversion, an acid value of 0.4 mg KOH/g, ester content >99.5% and EN 14214 compliance for all parameters measured. Nine blends of biodiesel (BD, 10%–30% vol.), n-butanol (BU, 5%–15% vol.) and BS-VI diesel were prepared and characterised for kinematic viscosity (2.34–2.90 cSt), calorific value (40,683.12–44,901.66 kJ/kg), density (856.4–875.4 kg/m3), flash point (54–58 °C) and fire point (61–69 °C). Ranking the blends by their normalised Euclidean distance from the measured diesel across the five properties placed 10% BD + 15% BU and 30% BD + 15% BU closest; these are reported as candidates for engine-performance and emissions testing. A support vector regression model with leave-one-out cross-validation (LOOCV R2 = 0.73–0.90) screened intermediate compositions. Because hyperparameter selection was not nested within each fold, these metrics may remain optimistically biased and are not evidence of generalised predictive capability. The work demonstrates laboratory-scale SEPO valorisation into standards-compliant biodiesel and screening-level blend selection; engine performance, emissions and lifecycle evaluation remain future work.

Authors

Institutions

Publication Details

Journal
International Journal of Sustainable Engineering
Published
2026-11-19
DOI
https://doi.org/10.1080/19397038.2026.2751774
Primary Topic
Biodiesel Production and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Production of biodiesel from Spent Earth Palm Oil and machine learning-based characterisation of ternary blends

Nagesh Siraganahalli Narasimhaiah, Ramachandra Chamarajanagar Gopal, Raghavendra Madhava Deshpande
International Journal of Sustainable Engineering
Biodiesel Production and Applications
article

Production of biodiesel from Spent Earth Palm Oil and machine learning-based characterisation of ternary blends

Nagesh Siraganahalli Narasimhaiah, Ramachandra Chamarajanagar Gopal, Raghavendra Madhava Deshpande
article en

Abstract

Spent earth palm oil (SEPO), a high FFA (32.85%) palm refining waste, was converted to biodiesel in steps: a two acid esterification brought the acid value below 2 mg KOH/g, and base-catalysed transesterification yielded 95% conversion, an acid value of 0.4 mg KOH/g, ester content >99.5% and EN 14214 compliance for all parameters measured. Nine blends of biodiesel (BD, 10%–30% vol.), n-butanol (BU, 5%–15% vol.) and BS-VI diesel were prepared and characterised for kinematic viscosity (2.34–2.90 cSt), calorific value (40,683.12–44,901.66 kJ/kg), density (856.4–875.4 kg/m3), flash point (54–58 °C) and fire point (61–69 °C). Ranking the blends by their normalised Euclidean distance from the measured diesel across the five properties placed 10% BD + 15% BU and 30% BD + 15% BU closest; these are reported as candidates for engine-performance and emissions testing. A support vector regression model with leave-one-out cross-validation (LOOCV R2 = 0.73–0.90) screened intermediate compositions. Because hyperparameter selection was not nested within each fold, these metrics may remain optimistically biased and are not evidence of generalised predictive capability. The work demonstrates laboratory-scale SEPO valorisation into standards-compliant biodiesel and screening-level blend selection; engine performance, emissions and lifecycle evaluation remain future work.

International Journal of Sustainable EngineeringVol. 19(1)
Presidency University (IN), Ramaiah Institute of Technology (IN), Visvesvaraya Technological University (IN)
Biodiesel Production and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon