Abstract
In multi-principal element alloys (MPEAs), the vast compositional design space and limited availability of microstructure-resolved corrosion data pose significant challenges to the predictive design of corrosion-resistant compositions. Traditional approaches rely heavily on trial-and-error experimentation and detailed microstructural characterization, which are time-consuming and resource-intensive. In this work, we develop a microstructure-agnostic deep learning framework that predicts the corrosion resistance of Co-Cr-Fe-Ni MPEAs directly from composition-based descriptors. By integrating physics-informed features, active learning, and uncertainty quantification, the model captures key physicochemical trends without requiring explicit structural input. The framework rapidly identifies non-equiatomic compositions with superior corrosion resistance, validated experimentally to outperform 304 L stainless steel under both acidic and chloride-rich conditions. Fundamental insights into corrosion mechanisms were obtained by linking model-predicted corrosion trends with electronic structure properties from density functional theory (DFT). The most corrosion-resistant compositions—e.g., Fe34Cr34 and Co34Cr34—exhibit high electron work functions and oxygen binding energies, indicative of strong passivation tendencies. Atom probe tomography (APT) of corroded surfaces confirms that these alloys form thinner (∼9 nm) and more protective passive films compared to conventional Cr-rich MPEAs (∼14 nm). Feature importance analysis within the machine learning model aligns with DFT-calculated elemental contributions to surface energetics, revealing a consistent ranking of Cr > Fe > Co > Ni in promoting passivation.
| Original language | English |
|---|---|
| Article number | 121619 |
| Journal | Acta Materialia |
| Volume | 301 |
| DOIs | |
| State | Published - Dec 1 2025 |
Funding
The authors gratefully acknowledge funding provided by US National Science Foundation (DMR-2104655). This work used shared facilities at the Nanoscale Characterization and Fabrication Laboratory, which is funded and managed by Virginia Tech’s Institute for Critical Technology and Applied Science. DB and CD express their gratitude to the NSERC Alliance International Catalyst Fund (ALLRP-2024–592696), Canada, for supporting the DFT study conducted in this work. Additional support is provided by the Virginia Tech National Center for Earth and Environmental Nanotechnology Infrastructure (NanoEarth), a member of the National Nanotechnology Coordinated Infrastructure (NNCI), supported by NSF (ECCS 1542100 and ECCS 2025151). APT research was supported by the Center for Nanophase Materials Sciences (CNMS), which is a US Department of Energy, Office of Science User Facility at Oak Ridge National Laboratory. The authors would like to thank James Burns for assistance in performing APT sample preparation and running the APT experiments. We sincerely thank Prof. Alan Druschitz at Virginia Tech for assistance with arc melting experiment in the Kroehling Advanced Materials Foundry. HS, XF, AL, ZL, and PKL very much appreciate the support of the National Science Foundation (DMR-1611180, 1809640, and 2226508), the Army Research Office Project (W911NF-13–1–0438 and W911NF-19–2–0049), the Department of Energy (DOE DE-EE0011185), and the Air Force Office of Scientific Research (AF AFOSR-FA9550–23–1–0503). We dedicate this work to the memory of Dr. Jonathan Poplawsky (ORNL), whose expertise, generosity, and kindness greatly shaped this study.
Keywords
- APT
- Alloys
- Corrosion
- DFT
- Machine learning
- Multicomponent