Predicting the corrosion properties of cast and hot isostatic pressed CoCrMo/W alloys in seawater by machine learning

Purpose Cobalt-based alloys exhibit a unique combination of wear resistance, strength and corrosion resistance. Localized corrosion of such alloys in seawater system can be several orders of magnitude faster than general corrosion, and direct experimental evidence of the local activation process is still lacking, which makes the accurate prediction for properties difficult, especially for long-term corrosion. The purpose of this study is revealing the relationship between multiple environments and corrosion properties to predict the corrosion of cobalt-based alloys. Design/methodology/approach A data-driven method for the prediction of the corrosion behavior of cast and hot isostatic-pressed CoCrMo/W alloys in seawater is proposed. The gradient boosting regression models calculate mean relative errors (MREs) of 0.160 and 0.435 by evaluating a hold-out set for breakdown potential (E b ) and maximum current density (i max ), respectively, considering various compositions, synthesis methods and corrosion environments. Findings The models can be used to estimate the “unseen” cobalt-based alloy after immersion in 3.5 Wt.% NaCl solution for one, two, four and eight months to obtain high precision with MREs of 7.8% and 9.8% for E b and i max , respectively. Originality/value Machine learning method provides novel and promising insights for the prediction of localized corrosion properties.