Computer modelling of the enrichment process of sunflower and corn oils with olive leaves through ultrasound treatment


ŞAMLI R., AYDIN Z., Sahin S.

BIOMASS CONVERSION AND BIOREFINERY, cilt.12, sa.12, ss.5571-5581, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 12 Sayı: 12
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s13399-020-00974-w
  • Dergi Adı: BIOMASS CONVERSION AND BIOREFINERY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC
  • Sayfa Sayıları: ss.5571-5581
  • Anahtar Kelimeler: ANN, Food additives, MLR, Modelling, Phenolic content, Vegetable oils
  • İstanbul Üniversitesi Adresli: Evet

Özet

Sunflower and corn oil can be enriched in polyphenols by adding olive leaf extracts to be used commercially. In this paper, Artificial Neural Networks (ANN), Multiple Linear Regression (MLR) and 11 different computer modelling techniques were simulated and compared in order to decide which method was the most appropriate to predict and optimise total phenolic content (TPC) after ultrasound-assisted extraction (UAE) when olive leaf extracts were added. The extraction conditions were olive leaf content (2000-6000 ppm), time (15-45 min) and amplitude (20-30%). TheR(2)values of ANN and MLR are 0.85 and 0.51 for sunflower oil enrichment and 0.88 and 0.66 for corn oil enrichment simulations which show that both of the modelling processes were performed successfully and produced acceptable results. ANN was proved to have the least error rate in all of the techniques according to the error function values as mean absolute error (MAE) and root mean squared error (RMSE). The values of ANN were measured as 1.52 and 1.17 as MAE and 1.85 and 1.37 as RMSE for sunflower oil and corn oil simulations, respectively.