# Experimental Investigation and Artificial Intelligence-Based Modeling of Novel Biodiesel Fuels Containing Hybrid Nanoparticle Additives

## TL;DR

This study explores how adding hybrid nanoparticles to biodiesel improves engine performance and reduces emissions, with strong AI predictions of the results.

## Contribution

The novelty lies in combining hybrid NiO–SiO2 nanoparticles with biodiesel and using AI modeling to predict and validate emission reductions.

## Key findings

- Adding 100 ppm NiO–SiO2 nanoparticles reduced CO, HC, and smoke emissions by up to 39.50% compared to diesel.
- The WSOB20 biodiesel blend with 100 ppm nanoparticles maintained high thermal efficiency while lowering emissions.
- A linear regression model accurately predicted CO emissions with low mean squared error (1.08 × 10−5).

## Abstract

This work investigates the influence of hybrid NiO–SiO2 nanoparticles on the engine behavior of biodiesel derived from waste sunflower oil and evaluates the experimental outcomes using a data-driven modeling approach. Biodiesel was produced via transesterification and doped with nanoparticles at concentrations of 50, 75, and 100 ppm. Performance and emission tests were conducted on a single-cylinder diesel engine operating at constant speed under varying loads. Specific fuel consumption, brake thermal efficiency, CO, HC, NOx, smoke opacity, and exhaust gas temperature were recorded and analyzed. The incorporation of nanoparticles improved combustion quality and contributed to substantial reductions in harmful emissions. The WSOB20 blend containing 100 ppm NiO–SiO2 provided the most balanced results, decreasing CO, HC, and smoke emissions by 39.50%, 39.40%, and 35.20%, respectively, relative to diesel fuel, while preserving competitive thermal efficiency. A linear regression model developed for CO prediction produced a low mean squared error (1.08 × 10−5), indicating strong predictive capability. The findings confirm that hybrid nanoparticle additives can enhance biodiesel performance while supporting accurate emission forecasting.