Optimizacija i predviđanje doze koagulanta za uklanjanje organskih mikrozagađivala na temelju podataka o zamućenju

In this study, four different mathematical models were considered to predict the coagulant dose in view of turbidity removal: response surface methodology (RSM), artificial neural networks (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). The results showed that all models accurately fitted the experimental data, even if the ANN model was slightly above the other models. The SVM model led to almost similar results as the ANN model; the only difference was in the validation phase, since the correlation coefficient was very high and the statistical indicators were very low for the ANN model compared to the SVM model. However, from an economic point of view, the SVM model was more appropriate than the ANN model, since its number of parameters was 22, i.e., almost half the number of parameters of the ANN model (43 parameters), while the results were almost similar in all the data phase. To reduce the economic costs further, the RSM model can also be used, which remained very useful due to its high coefficients related to the number of parameters – only 13. In addition, the statistical indicators of the RSM model remained acceptable. This work is licensed under a Creative Commons Attribution 4.0 International License.Četiri različita matematička modela primijenjena su za predviđanje doze koagulanta u svrhu uklanjanja zamućenja: model odzivne površine (RSM), umjetna neuronska mreža (ANN), model potpornih vektora (SVM) i model prilagodljivog sustava neizrazitog zaključivanja zasnovanog na neuronskoj mreži (ANFIS). Rezultati su pokazali da svi modeli točno opisuju eksperimentalne podatke, iako je ANN model bio nešto bolji. SVM model imao je sličnu podudarnost kao i ANN model no razlika je bila u validaciji modela gdje je ANN model ostvario vrlo visoke vrijednosti koeficijenta korelacije te niske vrijednosti statističkih pokazatelja. No s ekonomskog gledišta, SVM model je prikladniji od ANN modela, budući da je njegov broj parametara 22 što je gotovo upola manje od broja parametara ANN modela (43 parametra), dok su rezultati bili slični. Dodatno smanjenje ekonomskih troškova može se ostvariti primjenom RSM modela koji je ostvario visoke vrijednosti koeficijenata s obzirom na svega 13 parametara. Uz to, RSM model imao je prihvatljive statističke pokazatelje. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna