Optimal performance of COD removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network

Abstract

A direct and inverse artificial neural network (ANN and ANNi) approach was developed to predict the chemical oxygen demand (COD) removal during the degradation of alazine and gesaprim commercial herbicides under various experimental conditions. The configuration 9–9–1 (9 inputs, 9 hidden and 1 output neurons) presented an excellent agreement (R 2 = 0.9913) between experimental and simulated COD value considering the hyperbolic tangent sigmoid and linear transfer function in the hidden layer and output layer. The sensitivity analysis showed that all studied input variables (reaction time, pH, herbicide concentration, contaminant, US ultrasound, UV light intensity, [TiO 2] o,[K 2S 2O 8] o, and SR solar radiation) have strong effect on the degradation of the commercial herbicide in terms of COD removal. In addition, reaction time is the most influential parameter with relative importance of 33.49%, followed by initial herbicide concentration. COD optimal performance was carried out by inverting artificial neural network. Now, ANNi could calculate the optimal unknown parameter (reaction time) to obtain a COD required. Very low percentage of error and short computing makes this methodology attractive to be applied to the on-line control of Advanced Oxidation Process (AOP) over the degradation of commercial herbicide.