Answers are grounded in this paper and cite their sources.
Optimizing the transesterification process remains a complex challenge, requiring robust modelling and optimization techniques. This research explores an innovative strategy to maximize biodiesel yield from neem oil by optimizing key process parameters through the use of a heterogeneous nanocatalyst synthesized from luffa fibre. The nanocatalyst was fabricated via the sol-gel method and extensively characterized using SEM-EDX, FT-IR, XRD, BET, and TGA techniques. Three-dimensional response surface plots indicated that the process variables significantly affected biodiesel output. Analysis of Variance (ANOVA) confirmed the adequacy of a second-order polynomial model with an R² of 0.9293, adjusted R² of 0.8727, and predicted R² of 0.7171, reflecting a strong relationship between predicted and experimental results. In contrast, the Artificial Neural Network (ANN) model attained a higher accuracy with an R² of 0.999 and a mean squared error (MSE) of 1.0757 × 10⁻¹⁰ after 100 epochs. A hybrid approach combining Particle Swarm Optimization (PSO) and ANN was implemented to enhance biodiesel yield while conserving resources. The PSO-ANN model yielded an optimal conversion rate of 98.83%, outperforming PSO (96.45%) and the Response Surface Methodology (RSM) model (92.099%). The optimum conditions for PSO-ANN were a reaction time of 1.52 h, temperature of 40.3 °C, methanol-to-oil ratio of 10.04.: 1, catalyst loading of 2.41 wt.%, and an agitation speed of 303.1 rpm. In contrast, RSM's optimal conditions required longer time and higher energy input: 1.65 h, 43.25 °C, a 10.98:1 methanol-to-oil ratio, 2.59 wt.% catalyst, and 419.579 rpm agitation. The superior performance of the PSO-ANN model demonstrates its potential for accurately predicting and optimizing biodiesel production, significantly reducing experimental trials. Furthermore, the produced neem-based biodiesel complied with ASTM D6751 quality standards, underscoring its viability as a green fuel alternative
No takes yet. Share an insight, caveat, or question.
Nwosu-Obieogu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: