Electrolysis of 250 mL of OTC solutions (30 mg/L) were carried out in an undivided electrolytic cell in galvanostatic mode. We investigated the effect of operating parameters such as, nature (Na2SO4, NaNO3, KNO3 and NaCl) and dose of electrolyte support (20-100nmM), solution pH (3-11) and current intensity (50-400 mA), on removal efficiency. The results showed that the anodic oxidation method can be used efficiently for OTC degradation and the optimal operating conditions were 40 mM of Na2SO4, pH 4.3 (natural pH of solution) and 300 mA. At these optimal conditions and after 180 min of treatment, more than 96% of the initial OTC concentration was removed and the corresponding specific energy consumption was 4.5 kWh/kg OTC. Subsequently, an artificial neural network (ANN) was developed to model the performance of anodic oxidation process based on experimental degradation data. The Levenberg-Marquardt back propagation algorithm with the sigmoid transfer function (logsig) at the hidden layer, and a linear transfer function (purelin) at the output layer were used. Single hidden layer with 14 neurons presented the best values for the mean squared error (MSE) and the correlation coefficient (R), with respectively corresponding values of 0.0002 and 0.99. (C) 2017 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.