본문 바로가기

Learning From Atoms: Machine Learning Enabled Design of Durable PtCo Fuel Cell Catalysts

문서 유형
연구출판물 · 학술지 논문
등재
Nature IndexSCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
ADVANCED FUNCTIONAL MATERIALS36(80) · 2026
피인용
Web of Science 0Scopus 0
FWCI (Scopus)
0
JCR IF
JCR 2024 19
ISSN
1616-301X

저자

  1. Lee, Jong Min제1저자Korea Inst Energy Res KIER, Hydrogen Energy Inst, Hydrogen Res & Demonstrat Ctr, Daejeon, Jeollabuk Do, South Korea
  2. Jin, SongKorea Inst Mat Sci KIMS, Energy & Environm Mat Res Div, Chang Won, Gyeongnam, South Korea
  3. Hwang, JeeminKorea Inst Energy Res KIER, Hydrogen Energy Inst, Hydrogen Res & Demonstrat Ctr, Daejeon, Jeollabuk Do, South Korea
  4. Kang, Mun SeonUNITUS Co Ltd, PFC Prod Team, Chungju si, Chungcheongbuk, South Korea
  5. 강준희Pusan Natl Univ, Dept Nano Fus Technol, Busan, South Korea
  6. Choi, Sung Mook교신저자Korea Inst Mat Sci KIMS, Energy & Environm Mat Res Div, Chang Won, Gyeongnam, South Korea
  7. Seo, Min Ho교신저자Pukyong Natl Univ, Dept Nanotechnol Engn, Busan, South Korea

초록

Predicting electrocatalyst performance under realistic conditions remains challenging due to the limitations of quantum mechanical (QM) methods. Recent advances in artificial intelligence (AI) have enabled data-driven potentials that bridge quantum accuracy with realistic and nanoscale catalyst modeling. Here, a computational-experimental approach is presented to investigate the oxygen reduction reaction (ORR) activity and durability of intermetallic PtCo nanoparticles by integrating QM calculations with neural network potential (NNP) based real-sized simulation. The NNP, trained on Pt, Co, and PtCo systems, enabled accurate modeling of nanoparticles up to 5 nm containing several thousand atoms. ORR activity was elucidated through analysis of the d-band center, oxygen adsorption energies, free energy diagrams, and validated by rotating disk electrode (RDE) measurements. Dissolution potentials (Udiss) calculated via NNP revealed strong dependence on core configuration and particle size, with onion-like ordered PtCo showing the highest Udiss. These trends were experimentally validated through accelerated durability tests (ADT), and the consistency between NNP and QM results confirms the model's predictive reliability. This combined theoretical and experimental approach provides a reliable and scalable pathway for understanding degradation mechanisms and designing durable fuel cell electrocatalysts.

키워드

artificial intelligenceintermetallic nanostructurenanoparticlePEMFCquantum mechanics

식별자

Scopus EID
2-s2.0-105040755377
WoS UID
001781388900001