Exploring the potential of transfer learning in extrapolating accelerated corrosion test data for long-term atmospheric corrosion forecasting

Abstract

This study utilizes transfer learning (TL) to enhance long-term atmospheric corrosion predictions. Using a Fe/Cu galvanic-type sensor, we gathered data in a controlled SAE J2334 salt spray setting and transferred this to an uncontrolled outdoor environment. Among TL methods tested, freezing the initial layer and fine-tuning others at a lower rate was most effective. The approach excelled at forecasting outdoor corrosion behaviour using a limited dataset. This approach could provide a solution to extrapolate results from controlled corrosion tests to unpredictable outdoor conditions and addressing data scarcity in machine learning modelling in the context of atmospheric corrosion.