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

Tu Ngoc Lam; Jiajun Jiang; Min Cheng Hsu; Shr Ruei Tsai; Mao Yuan Luo; Shuo Ting Hsu; Wen Jay Lee; Chung Hao Chen; E. Wen Huang

doi:10.3390/ma17194754

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

Tu Ngoc Lam, Jiajun Jiang, Min Cheng Hsu, Shr Ruei Tsai, Mao Yuan Luo, Shuo Ting Hsu, Wen Jay Lee, Chung Hao Chen^*, E. Wen Huang^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

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 ZrO₂-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.

Original language	English
Article number	4754
Journal	Materials
Volume	17
Issue number	19
DOIs	https://doi.org/10.3390/ma17194754
State	Published - Oct 2024

Keywords

linear regression
machine learning
random forest
shape-memory alloys
support vector regression

Access to Document

10.3390/ma17194754

Cite this

@article{d8107585437642888492f1a9c217df5f,

title = "Predictions of Lattice Parameters in NiTi High-Entropy Shape-Memory Alloys Using Different Machine Learning Models",

abstract = "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 ZrO2-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 ac, am, bm, and cm in NiTi-based HESMAs, while RF excelled in computing βm 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.",

keywords = "linear regression, machine learning, random forest, shape-memory alloys, support vector regression",

author = "Lam, {Tu Ngoc} and Jiajun Jiang and Hsu, {Min Cheng} and Tsai, {Shr Ruei} and Luo, {Mao Yuan} and Hsu, {Shuo Ting} and Lee, {Wen Jay} and Chen, {Chung Hao} and Huang, {E. Wen}",

note = "Publisher Copyright: {\textcopyright} 2024 by the authors.",

year = "2024",

month = oct,

doi = "10.3390/ma17194754",

language = "English",

volume = "17",

journal = "Materials",

issn = "1996-1944",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "19",

}

TY - JOUR

T1 - Predictions of Lattice Parameters in NiTi High-Entropy Shape-Memory Alloys Using Different Machine Learning Models

AU - Lam, Tu Ngoc

AU - Jiang, Jiajun

AU - Hsu, Min Cheng

AU - Tsai, Shr Ruei

AU - Luo, Mao Yuan

AU - Hsu, Shuo Ting

AU - Lee, Wen Jay

AU - Chen, Chung Hao

AU - Huang, E. Wen

PY - 2024/10

Y1 - 2024/10

N2 - 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 ZrO2-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 ac, am, bm, and cm in NiTi-based HESMAs, while RF excelled in computing βm 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.

AB - 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 ZrO2-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 ac, am, bm, and cm in NiTi-based HESMAs, while RF excelled in computing βm 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.

KW - linear regression

KW - machine learning

KW - random forest

KW - shape-memory alloys

KW - support vector regression

UR - http://www.scopus.com/inward/record.url?scp=85206683879&partnerID=8YFLogxK

U2 - 10.3390/ma17194754

DO - 10.3390/ma17194754

M3 - Article

AN - SCOPUS:85206683879

SN - 1996-1944

VL - 17

JO - Materials

JF - Materials

IS - 19

M1 - 4754

ER -

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

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this