Answers are grounded in this paper and cite their sources.
Explores biodiesel production optimization from watermelon seed oil, indicating advanced modeling benefits.
This study focuses on the application of Artificial Neural Networks (ANN) for the predictive modeling and optimization of biodiesel production from watermelon (Citrullus lanatus) seed oil using a lipase-doped coconut husk ash catalyst. The transesterification process parameters catalyst concentration, methanol-to-oil molar ratio, reaction time, temperature, and agitation speed were systematically investigated and the results were analyzed using ANN. A multi-input-single-output (MISO) feed-forward back-propagation ANN model with a Levenberg-Marquardt training algorithm was developed. The ANN model demonstrated excellent predictive accuracy with a mean square error (MSE) of 0.39412 and an R² of 0.99926, outperforming the RSM model (R² = 0.9933, MSE = 1.07). The optimal process conditions identified by RSM were: catalyst concentration of 1.36 wt%, methanol-to-oil ratio of 9.49:1, reaction time of 3.01 hours, temperature of 50.97 °C, and agitation speed of 239.44 rpm, yielding a biodiesel production efficiency of 77.79%. The produced biodiesel exhibited favorable fuel properties, including a cetane number of 50.97 and a calorific value of 44.565 MJ/kg. This study establishes that ANN-based modeling provides superior predictive capability for nonlinear biodiesel transesterification processes, offering a robust tool for process optimization and scale-up.
No takes yet. Share an insight, caveat, or question.
Umunna et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: