Predictions of Lattice Parameters in NiTi High-Entropy Shape-Memory Alloys Using Different Machine Learning Models.

Autor:	Lam TN; Department of Materials Science and Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan.; Department of Physics, College of Education, Can Tho University, Can Tho City 900000, Vietnam., Jiang J; Electrical and Computer Engineering Department, Old Dominion University, Norfolk, VA 23529, USA., Hsu MC; Department of Materials Science and Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan., Tsai SR; Computer Science and Information Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan., Luo MY; Department of Materials Science and Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan., Hsu ST; Department of Materials Science and Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan., Lee WJ; National Center for High-Performance Computing, Taichung City 40763, Taiwan., Chen CH; Electrical and Computer Engineering Department, Old Dominion University, Norfolk, VA 23529, USA., Huang EW; Department of Materials Science and Engineering, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 30010, Taiwan.; High Entropy Materials Center, National Tsing Hua University, Hsinchu 30013, Taiwan.; Department of Materials Science and Engineering, Case Western Reserve University, Cleveland, OH 44106, USA.
Jazyk:	angličtina
Zdroj:	Materials (Basel, Switzerland) [Materials (Basel)] 2024 Sep 27; Vol. 17 (19). Date of Electronic Publication: 2024 Sep 27.
DOI:	10.3390/ma17194754
Abstrakt:	This work applied three machine learning (ML) models-linear regression (LR), random forest (RF), and support vector regression (SVR)-to predict the lattice parameters of the monoclinic B19' phase in two distinct training datasets: previously published ZrO 2 -based shape-memory ceramics (SMCs) and NiTi-based high-entropy shape-memory alloys (HESMAs). Our findings showed that LR provided the most accurate predictions for a c , a m , b m , and c m in NiTi-based HESMAs, while RF excelled in computing β m for both datasets. SVR disclosed the largest deviation between the predicted and actual values of lattice parameters for both training datasets. A combination approach of RF and LR models enhanced the accuracy of predicting lattice parameters of martensitic phases in various shape-memory materials for stable high-temperature applications.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.