Soft Computing Prediction of Oil Extraction from Huracrepitan Seeds

This study analyses the extraction process parameters of huracrepitan seed oil using the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). The experiments were conducted at temperature (60–80 °C), time (4–6 h), and solute/solvent ratio (0.05–0.10) with output parameter as oil yield. Sensitivity analysis shows that temperature and time had the most significant effect on the oil yield. The oil yield estimation performance indicators are: ANN ( R 2 = 0.999, MSE = 5.63192E-13), ANFIS ( R 2 = 0.36927, MSE = 0.42331). The results show that ANN gave a better prediction than ANFIS. Ovom studijom analizirani su procesni parametri ekstrakcije ulja iz sjemenki biljke Hura crepitans primjenom prilagodljivog neuroneizrazitog (neuro-fuzzy) sustava zaključivanja (ANFIS) i umjetne neuronske mreže (ANN). Pokusi su provedeni pri temperaturi 60 – 80 °C, vremenu 4 – 6 h i omjeru otopljene tvari/otapala 0,05 – 0,10 s prinosom ulja kao izlaznim parametrom. Analiza osjetljivosti pokazala je da su temperatura i vrijeme najznačajnije utjecali na prinos ulja. Pokazatelji procjene učinka prinosa ulja su: ANN ( R 2 = 0,999, MSE = 5,63192E-13), ANFIS ( R 2 = 0,36927, MSE = 0,42331). Rezultati su pokazali da je ANN dao bolje predviđanje od ANFIS-a.