Prediction of corrosion behavior using neural network as a data mining tool

Abstract

A supervised neural network (NN) method was used as a data mining tool to predict corrosion behavior of metal alloys. The NN model learned the underlying laws that map the alloy’s composition and environment to the corrosion rate. Existing corrosion data on corrosion allowable as well as corrosion resistive alloys were collected for both DC and AC corrosion experiments. The data mining results allow us to categorize and prioritize certain parameters (i.e. pH, temperature, time of exposure, electrolyte composition, metal composition, etc.) and help us understand the synergetic effects of the parameters and variables on electrochemical potentials and corrosion rates.