Niger Seed Oil-Based Biodiesel Production Using Transesterification Process: Experimental Investigation and Optimization for Higher Biodiesel Yield Using Box–Behnken Design and Artificial Intelligence Tools

The present work aims at cost-effective approaches for biodiesel conversion from niger seed (NS) oil by employing the transesterification process, Box–Behnken design (BBD), and artificial intelligence (AI) tools. performances of yield are reliant on variables (methanol-to-oil molar ratio M:O, reaction time Rt, catalyst concentration CC, temperature RT). BBD matrices representing parameters were utilized experiment reductions, analyzing factor (individual interaction) effects, deriving empirical equations, evaluating prediction accuracy. M:O showed a dominant effect, followed RT, respectively. All two-factor interaction effects significant, excluding two interactions (Rt with RT model good correlation or regression coefficient value equal to 0.9869. Furthermore, produced best fit, corresponding experimental predicted biodiesel. Three AI algorithms applied (the big-bang big-crunch algorithm (BB-BC), firefly (FA), grey wolf optimization (GWO)) search conditions that could maximize yield. GWO FA better fitness (biodiesel yield) values compared BB-BC. resulted in maximum 95.3 ± 0.5%. computation incurred optimizing was found be 0.8 s BB-BC, 1.66 GWO, 15.06 FA. determined optimized condition is recommended solution accuracy slight compromise time. physicochemical properties tested according ASTM D6751-15C; results agreement would appropriate use diesel engines.