Double-glow plasma surface alloying assisted by machine learning for a high-performance ZrN thin layer on CoCrFeNiZr 0.5 eutectic high-entropy alloy
To overcome the limited surface properties and low efficiency of trial-and-error in high-entropy alloys (HEAs), we integrate machine learning (ML) with double-glow plasma surface alloying. ML models trained on phase, hardness, and corrosion current density datasets identified CoCrFeNiZr 0.5 for its toughness and predicted a favorable phase, hardness, and corrosion resistance profile, which is expected to support nitride formation based on established Zr-N bonding chemistry. A ZrN-alloyed layer was then synthesized, increasing microhardness by 35.3% (from 450 to 609 HV). Corrosion resistance in 3.5 wt.% NaCl improved significantly: a 0.026 V positive shift in corrosion potential, a 50% reduction in corrosion current density, and a lower corrosion rate (0.0188 vs. 0.0463 mm/y).
Authors
- Mengdi Zhang (ORCID: https://orcid.org/0009-0009-2560-6440)
- He Zhang (ORCID: https://orcid.org/0009-0007-5719-9099)
- Yuqing Xie
- Hanqing Xu
- Gong Li
Institutions
- Yanshan University (CN)
- Hebei University (CN)
Publication Details
- Journal
- Materials Science and Technology
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1177/02670836261505210
- Primary Topic
- High Entropy Alloys Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Hebei Normal University of Science and Technology
- Innovative Research Group Project of the National Natural Science Foundation of China