Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure

Abstract The prediction of corrosion resistance in High-entropy alloys (HEAs) faces challenges due to previous machine learning methods not fully capturing the interdependencies between composition, processing, and crystal structure. This study proposes the Composition and Processing-Driven Two-Stag...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangxuan Song, Dongmei Fu, Yongjie Lin, Lingwei Ma, Dawei Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Materials Degradation
Online Access:https://doi.org/10.1038/s41529-025-00632-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769122989080576
author Guangxuan Song
Dongmei Fu
Yongjie Lin
Lingwei Ma
Dawei Zhang
author_facet Guangxuan Song
Dongmei Fu
Yongjie Lin
Lingwei Ma
Dawei Zhang
author_sort Guangxuan Song
collection DOAJ
description Abstract The prediction of corrosion resistance in High-entropy alloys (HEAs) faces challenges due to previous machine learning methods not fully capturing the interdependencies between composition, processing, and crystal structure. This study proposes the Composition and Processing-Driven Two-Stage Corrosion Prediction Framework with Structural Prediction (CPSP Framework), which first predicts crystal structure and then combines composition and processing data for corrosion current prediction. A deep learning model, Mat-NRKG, is developed based on the CPSP framework, efficiently integrating composition, processing, and crystal structure data through a knowledge graph and graph convolutional network. Evaluations using the HEA-CRD dataset show that the CPSP Framework outperforms the Composition-Only Prediction Framework (CP Framework) and the Composition and Processing-Based Prediction Framework (CPP Framework). The Mat-NRKG model demonstrates the best performance on the HEA-CRD dataset. Its generalization capability is validated through experiments on five laboratory-synthesized HEAs, highlighting the effectiveness of incorporating prior knowledge into model design for performance prediction.
format Article
id doaj-art-8bb4278d21684acc94cb93bc541c2b4c
institution DOAJ
issn 2397-2106
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Materials Degradation
spelling doaj-art-8bb4278d21684acc94cb93bc541c2b4c2025-08-20T03:03:34ZengNature Portfolionpj Materials Degradation2397-21062025-07-019111210.1038/s41529-025-00632-4Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structureGuangxuan Song0Dongmei Fu1Yongjie Lin2Lingwei Ma3Dawei Zhang4Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology BeijingBeijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology BeijingNational Materials Corrosion and Protection Data Center, University of Science and Technology BeijingNational Materials Corrosion and Protection Data Center, University of Science and Technology BeijingNational Materials Corrosion and Protection Data Center, University of Science and Technology BeijingAbstract The prediction of corrosion resistance in High-entropy alloys (HEAs) faces challenges due to previous machine learning methods not fully capturing the interdependencies between composition, processing, and crystal structure. This study proposes the Composition and Processing-Driven Two-Stage Corrosion Prediction Framework with Structural Prediction (CPSP Framework), which first predicts crystal structure and then combines composition and processing data for corrosion current prediction. A deep learning model, Mat-NRKG, is developed based on the CPSP framework, efficiently integrating composition, processing, and crystal structure data through a knowledge graph and graph convolutional network. Evaluations using the HEA-CRD dataset show that the CPSP Framework outperforms the Composition-Only Prediction Framework (CP Framework) and the Composition and Processing-Based Prediction Framework (CPP Framework). The Mat-NRKG model demonstrates the best performance on the HEA-CRD dataset. Its generalization capability is validated through experiments on five laboratory-synthesized HEAs, highlighting the effectiveness of incorporating prior knowledge into model design for performance prediction.https://doi.org/10.1038/s41529-025-00632-4
spellingShingle Guangxuan Song
Dongmei Fu
Yongjie Lin
Lingwei Ma
Dawei Zhang
Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
npj Materials Degradation
title Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
title_full Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
title_fullStr Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
title_full_unstemmed Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
title_short Corrosion resistance prediction of high-entropy alloys: framework and knowledge graph-driven method integrating composition, processing, and crystal structure
title_sort corrosion resistance prediction of high entropy alloys framework and knowledge graph driven method integrating composition processing and crystal structure
url https://doi.org/10.1038/s41529-025-00632-4
work_keys_str_mv AT guangxuansong corrosionresistancepredictionofhighentropyalloysframeworkandknowledgegraphdrivenmethodintegratingcompositionprocessingandcrystalstructure
AT dongmeifu corrosionresistancepredictionofhighentropyalloysframeworkandknowledgegraphdrivenmethodintegratingcompositionprocessingandcrystalstructure
AT yongjielin corrosionresistancepredictionofhighentropyalloysframeworkandknowledgegraphdrivenmethodintegratingcompositionprocessingandcrystalstructure
AT lingweima corrosionresistancepredictionofhighentropyalloysframeworkandknowledgegraphdrivenmethodintegratingcompositionprocessingandcrystalstructure
AT daweizhang corrosionresistancepredictionofhighentropyalloysframeworkandknowledgegraphdrivenmethodintegratingcompositionprocessingandcrystalstructure