Key points are not available for this paper at this time.
The study aims to employ machine learning modelling approach to model the measurement of corrosion rate on AISI 316 stainless steel when corrosion inhibitor is added in different dosages and dose schedules. To achieve this, experimental data was analyzed statistically and modeled using Levenberg-Marquardt’s back-propagation artificial neural network (LMBP-ANN), and adaptive neuro-fuzzy inference system (ANFIS) algorithms. Maximum inhibition efficiencies of 96.44%, 94.74%, and 90.24% were obtained from experimental at a concentration of 10 g and temperatures of 288, 298, and 308 K respectively. The experiment shows that the corrosion rate time profile depends on the dosing schedule, whereas the final rate mainly depends on the environmental severity. The corrosion rates are predicted by the developed models while their capabilities were compared in terms of Mean Absolute Percentage Error root (MAPE), determination coefficient (R2), Mean Absolute Deviation (MAD), and Root Mean Square Error (RMSE) for all outputs. From the statistical metrics obtained, credence was given to ANFIS as the best predictive model compared to the LMBP-ANN with MAPE, R2, MAD, and RMSE value of 15.242,0.893, 0.105,0.372 for corrosion rate, 13.135,0.904, 0.725,1.036, for weight loss and 18.342, 0.835, 20.417, 24.238 for inhibition efficiency at the testing stage. The effect of inhibitor concentration and exposure time are the most significant parameters for predicting eggshell extract as potential inhibitor for stainless steel in oilfield pickling and acidizing media.
Sanni et al. (Mon,) studied this question.