Artificial Intelligence Assisted Ultrasonic Extraction of Total Flavonoids from Rosa sterilis

Abstract

Flavonoids in Rosa sterilis were studied. The flavonoids in Rosa sterilis were extracted by ultrasonic method, and the extraction conditions were modeled and optimized by response the surface methodology and the artificial intelligence method. The results show that the ultrasonic method can effectively extract total flavonoids, and the extraction rate is close to the prediction value of ANN-GA algorithm, which proves the rationality of the model. The order of the effects of the parameters on the experiment was material liquid ratio > extraction power > extraction time > ethanol concentration. In addition, the scavenging effects of flavonoids on DPPH, O2−· and ·OH were also determined, and these indicated that flavonoids have strong antioxidant activities. The kinetics of the extraction process was studied by using the data of the extraction process, and it was found that the extraction process conformed to Fick’s first law.