首页|Findings from University of Maryland Provides New Data on Machine Learning (A Ma chine Learning Interatomic Potential for High Entropy Alloys)
Findings from University of Maryland Provides New Data on Machine Learning (A Ma chine Learning Interatomic Potential for High Entropy Alloys)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Data detailed on Machine Learning have been prese nted. According to news reporting originating in College Park, Maryland, by News Rx journalists, research stated, "High entropy alloys (HEAs) possess a vast comp ositional space, providing exciting prospects for tailoring material properties yet also presenting challenges in their rational design. Efficiently achieving a well -designed HEA often necessitates the aid of atomistic simulations, which r ely on the availability of high -quality interatomic potentials." Financial support for this research came from Oracle. The news reporters obtained a quote from the research from the University of Mar yland, "However, such potentials for most HEA systems are missing due to the com plex interatomic interaction. To fundamentally resolve the challenge of the rati onal design of HEAs, we propose a strategy to build a machine learning (ML) inte ratomic potential for HEAs and demonstrate this strategy using CrFeCoNiPd as a m odel material. The fully trained ML model can achieve remarkable prediction prec ision (>0.92 R 2 ) for atomic forces, comparable to the ab initio molecular dynamics (AIMD) simulations. To further validate the accurac y of the ML model, we implement the ML potential for CrFeCoNiPd in parallel mole cular dynamics (MD) code. The MD simulations can predict the lattice constant (1 % error) and stacking fault energy (10 % error) of CrFeCoNiPd HEAs with high accuracy compared to experimental results. Through sys tematic MD simulations, for the first time, we reveal the atomicscale deformatio n mechanisms associated with the stacking fault formation and dislocation crosss lips in CrFeCoNiPd HEAs under uniaxial compression, which are consistent with ex perimental observations. This study can help elucidate the underlying deformatio n mechanisms that govern the exceptional performance of CrFeCoNiPd HEAs."
College ParkMarylandUnited StatesN orth and Central AmericaAlloysCyborgsEmerging TechnologiesMachine Learni ngMolecular DynamicsPhysicsUniversity of Maryland
NETL
NSTL
