Comparative studies of Taguchi dynamic analysis, statistical, and artificial neural networks for low-carbon steel corrosion inhibition in acidic media

Abstract

The aim of the present work is to optimize the corrosion inhibition process of low-carbon steel in 2.5 M phosphoric acid at different temperatures and inhibitor concentrations. The weight loss method is used to evaluate the corrosion rate in the absence or presence of a corrosion inhibitor. Taguchi dynamic (L16), mathematical regression, and artificial neural networks (ANN) are used during the data processing. The outcomes showed that the %IE increased with inhibitor concentration and temperature up to 50 oC. The Taguchi method showed that the optimum conditions for the corrosion inhibition temperature were found to be 50 oC and a 0.05 M KI concentration. Two mathematical models are proposed to construct a relationship between %IE and independent variables: the exponent model (EM) and the polynomial model (PM). PM was more accurate than EM, with a significant correlation coefficient approaching 0.9851. Temperature had a greater effect on the %IE than inhibitor concentration, which was consistent with Taguchi's findings. In ANN analyses, five networks were suggested: linear, a generalized regression neural network (GRNN), radial basis functions (RBF), and two multi-layer perceptron (MLP) networks. The highest correlation coefficient (0.996) and lower absolute error (0.126) were achieved by MLP 2:2-9-4-1:1.