Modeling the environmental dependence of pit growth using neural network approaches

Corrosion pits have been shown to nucleate fatigue cracks, and this is a critical issue for aerospace aluminum alloys, which experience a variety of corrosive environments in service. Consequently, modeling pit growth as a function of environment is necessary. In this study, two orientations of AA7075-T651 blocks were boldly exposed in solutions of varying temperature, pH, and [Cl−] for three exposure times. Optical profilometry and Weibull functions were utilized to characterize pit depth and diameter distributions. Artificial neural networks were a powerful tool in effectively modeling maximum pit dimensions and Weibull parameters. In most environments, pit growth followed t1/3 kinetics.