Machine learning combined with solid solution strengthening model for predicting hardness of high entropy alloys
Authors:
- Yi-Fan ZhangYZYi-Fan Zhang
- Wei RenWei Ren
- Wei-Li WangWWWei-Li Wang
- Shu-Jian DingSDShu-Jian Ding
- Nan LiNLNan Li
- Liang ChangLCLiang Chang
- Qian ZhouQZQian Zhou
Open Access
- 1 January 2023
- journal article
- research article
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 72 (18) , 180701
Abstract
第一性原理、热力学模拟等传统的材料计算方法在高熵合金的设计中多用于合金相的预测,同时会耗费巨大的计算资源。本文以性能为导向,选用机器学习的算法建立了一个高熵合金硬度预测模型,并将机器学习与固溶体强化的物理模型相结合,使用遗传算法筛选出最具有代表性的3个特征参数,利用这3个特征构建的随机森林模型,其R2达到了0.9416,对高熵合金的硬度取得了较好的预测效果。本文选用的机器学习算法和3个材料特征在固溶体强化性质方面也有一定的预测效果。针对随机森林可解释性较差的问题,本文还利用SHAP可解释机器学习方法挖掘了机器学习模型的内在推理逻辑。Keywords
This publication has 34 references indexed in Scilit:
- Impact and usage of the shear thickening fluid (STF) material in damping vibration of bolted flange jointsSmart Materials and Structures, 2019
- Atomic and electronic basis for the serrations of refractory high-entropy alloysnpj Computational Materials, 2017
- EfficientAb initioModeling of Random Multicomponent AlloysPhysical Review Letters, 2016
- Tribological behavior of AlCoCrCuFeNi and AlCoCrFeNiTi0.5 high entropy alloys under hydrogen peroxide solution against different counterpartsTribology International, 2015
- Phase selection rules for cast high entropy alloys: An overviewMaterials Science and Technology, 2015
- Modelling solid solution hardening in high entropy alloysActa Materialia, 2015
- Atomic-size effect and solid solubility of multicomponent alloysScripta Materialia, 2015
- A refractory Hf25Nb25Ti25Zr25 high-entropy alloy with excellent structural stability and tensile propertiesMaterials Letters, 2014
- Design strategies for fluorescent biodegradable polymeric biomaterialsJournal of Materials Chemistry B, 2012
- A Statistical Theory of Solid Solution HardeningPhysica Status Solidi (b), 1970