Estimating pitting descriptors of 316 L stainless steel by machine learning and statistical analysis

Abstract

A hybrid rule-based/ML approach using linear regression and artificial neural networks (ANNs) determined pitting corrosion descriptors from high-throughput data obtained with Scanning Electrochemical Cell Microscopy (SECCM) on 316 L stainless steel. Non-parametric density estimation determined the central tendencies of the Epit/log(jpit) and Epass/log(jpass) distributions. Descriptors estimated using conditional mean or median curves were compared to their central tendency values, with the conditional medians providing more accurate results. Due to their lower sensitivity to high outliers, the conditional medians were more robust representations of the log(j) vs. E distributions. An observed trend of passive range shortening with increasing testing aggressiveness was attributed to delayed stabilisation of the passive film, rather than early passivity breakdown.

Five years of scanning electrochemical cell microscopy (SECCM): new insights and innovations

“…SECCM has proven to be a powerful tool for unravelling electrochemical phenomena on materials with complex surface structures, notably those used in structural applications such as low-carbon steel, 132 stainless steel, 133–135 and other metals 14,136 and metal alloys, 137,138 which are susceptible to corrosion during practical use. Beyond its use with classical voltammetric methods, SECCM has been recently combined with electrochemical impedance spectroscopy (EIS; explored further below), which allowed localised increases in charge transfer resistance (inversely proportional to the rate of corrosion) to be quantified at the interfaces of steel and Mg, potentially aiding in the prevention of galvanic corrosion.…”