Skip to content
DraconiticResearch
Search Sources API
186,625 studies31 sourcesUpdated 37 min ago
Peer-reviewedCC BYAdvanced Science

Interpretable Machine Learning Framework for Nb─Si Based Alloy Design with Enhanced Fracture Toughness

  • Dezhi Chen1,2
  • Chao Xu2
  • Jingyue Yu2
  • Qi Ming Wang2
  • Hongze Fang2
  • Shuo Yin1
  • Turab Lookman3,4
  • Ruirun Chen2
4 affiliations
  1. 1Department of Mechanical Manufacturing and Biomedical Engineering Trinity College University of Dublin Dublin Ireland
  2. 2National Key Laboratory For Precision Hot Processing of Metals Harbin Institute of Technology Harbin P. R. China
  3. 3AiMaterials Research LLC Santa Fe New Mexico USA
  4. 4State Key Laboratory For Mechanical Behavior of Materials State Key Laboratory of Porous Metal Materials School of Materials Science and Engineering Xi'an Jiatong University Xi'an P. R. China
Open at sourceDOICite

Abstract

A continuing challenge in aerospace materials is the search for alloys that have desired functional properties to operate at higher temperatures with lower densities. This improves aero‐engine efficiency and reduces CO 2 and other harmful emissions, aligning with aviation industry targets for emission reduction. Nb─Si alloys can operate at higher temperatures than current Ni‐based superalloys and have lower densities. We develop a machine learning‐driven design framework for Nb─Si based ultra‐high temperature alloys using a three‐step feature screening strategy to break the 20 MPa·m 1/2 fracture toughness barrier. Our model predicts fracture toughness ( K Q ) with an error <7%, and we use SHAP(ley) and PDP analysis to interpret the model to guide alloy design. Five alloys with Si content ranging from 3 to 15 at.% were synthesized to validate model predictions. Sample #5 (Nb 38.5 Ti 38.5 Si 3 Zr 18 V 2 ) achieved a K Q of 22.791 MPa·m 1/2 , exceeding the typical range (below 20 MPa·m 1/2 ) for as‐cast Nb─Si alloys. Microstructural analysis showed that the improved performance resulted from the transformation of brittle silicide phases to ductile Nbss phase and crack‐bridging toughening. Strengthening mechanism analysis reveals that solid solution strengthening was dominant (68%–84%), with excellent strength‐toughness balance.

Related

  1. The Role of Carbon Fibers in FFF 3D Printed Composites: A Comprehensive Review on the Effect on Mechanical Properties, Fracture Toughness, and Tribological Performance
    Lorenzo De Noni, Hengxi Chen
    PolymersPeer-reviewedCC BYFull textMaterials & polymersEurope PMC
  2. High temperature Nb-Si alloys using data science: optimization of fracture toughness and high-temperature strength
    Chao Xu, Dezhi Chen, Xiaofu Zhang +7
    Nature CommunicationsPeer-reviewedCC BY18 citedMaterials & polymersOpenAlex
  3. Experimental and Numerical Investigation of the Interfacial Bonding in Multi-Material Fused-Filament Fabrication Using Mode-I Fracture Toughness
    Ermias Wubete Fenta, Mohd Tauheed, Sarfaraz Ahmed Furquan +1
    PolymersPeer-reviewedCC BY 4.0Full textMaterials & polymersCrossrefEurope PMC
  4. Explainable CatBoost–TabPFN Hybrid for Mode-Resolved Interlaminar Fracture Toughness Prediction in Fiber-Reinforced Polymer Composites
    Md Arifuzzaman, Sayeed Rushd, Muhammad Ali Martuza +3
    PolymersPeer-reviewedCC BY 4.0Materials & polymersCrossref
  5. Predicting Glass Transition Temperature of Polyimide Homopolymers and Copolymers Using Interpretable QSPR-Based Machine Learning: The MFKit Framework
    Gleb Averochkin, Yulia Kirpal, Alexander Khina +7
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv

Cite

BibTeXRIS
BibTeX
@article{chen2026interpretable,
  title = {{Interpretable Machine Learning Framework for Nb─Si Based Alloy Design with Enhanced Fracture Toughness}},
  author = {Dezhi Chen and Chao Xu and Jingyue Yu and Qi Ming Wang and Hongze Fang and Shuo Yin and Turab Lookman and Ruirun Chen},
  journal = {Advanced Science},
  year = {2026},
  month = may,
  doi = {10.1002/advs.75815},
  url = {https://doi.org/10.1002/advs.75815},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Interpretable Machine Learning Framework for Nb─Si Based Alloy Design with Enhanced Fracture Toughness
AU  - Dezhi Chen
AU  - Chao Xu
AU  - Jingyue Yu
AU  - Qi Ming Wang
AU  - Hongze Fang
AU  - Shuo Yin
AU  - Turab Lookman
AU  - Ruirun Chen
PY  - 2026
DA  - 2026/05/25
JO  - Advanced Science
DO  - 10.1002/advs.75815
UR  - https://doi.org/10.1002/advs.75815
AB  - A continuing challenge in aerospace materials is the search for alloys that have desired functional properties to operate at higher temperatures with lower densities. This improves aero‐engine efficiency and reduces CO 2 and other harmful emissions, aligning with aviation industry targets for emission reduction. Nb─Si alloys can operate at higher temperatures than current Ni‐based superalloys and have lower densities. We develop a machine learning‐driven design framework for Nb─Si based ultra‐high temperature alloys using a three‐step feature screening strategy to break the 20 MPa·m 1/2 fracture toughness barrier. Our model predicts fracture toughness ( K Q ) with an error <7%, and we use SHAP(ley) and PDP analysis to interpret the model to guide alloy design. Five alloys with Si content ranging from 3 to 15 at.% were synthesized to validate model predictions. Sample #5 (Nb 38.5 Ti 38.5 Si 3 Zr 18 V 2 ) achieved a K Q of 22.791 MPa·m 1/2 , exceeding the typical range (below 20 MPa·m 1/2 ) for as‐cast Nb─Si alloys. Microstructural analysis showed that the improved performance resulted from the transformation of brittle silicide phases to ductile Nbss phase and crack‐bridging toughening. Strengthening mechanism analysis reveals that solid solution strengthening was dominant (68%–84%), with excellent strength‐toughness balance.
SN  - 2198-3844
ER  -