High entropy alloys for hydrogen storage applications: A machine learning-based approach DOI Creative Commons

N. Radhika,

Madabhushi Siri Niketh,

U.V. Akhil

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102780 - 102780

Published: Aug. 29, 2024

Hydrogen is a clean energy carrier and has potential applications in storage, power generation, transportation. This study explores the efficient safe storage of hydrogen, particularly through solid-state methods using high entropy alloys (HEAs). HEAs have garnered attention for their versatility tailoring properties hydrogen storage. The integration Machine Learning (ML) designing offers an expedited approach, analyzing datasets predicting material to enhance capacity, kinetics, stability. Despite significant progress, acknowledges certain research limitations, its relatively narrow focus on applying ML One biggest challenges with complexity, which. necessitates larger develop accurate predictive models. Collecting existing HEA data techniques main objective. Using algorithms like support vector regression (SVR), K-nearest (KNN), random forest (RF), hydrogen-to-metal ratio (H/M) valence electron configuration (VEC) are accurately predicted. proposes formation, identifying 741 quaternary 631 quinary HEAs. These compositions newly proposed do not yet exist. Out these, 774 identified as candidates applications. Applying techniques, selection process more efficient, reducing dependency time-consuming experiments making it easier discover promising candidates.

Language: Английский

Accelerated design of high-entropy alloy coatings for high corrosion resistance via machine learning DOI
Hongxu Cheng, Hong Luo, C.G. Fan

et al.

Surface and Coatings Technology, Journal Year: 2025, Volume and Issue: unknown, P. 131978 - 131978

Published: Feb. 1, 2025

Language: Английский

Citations

1
A Short Review: Tribology in Machining to Understand Conventional and Latest Modeling Methods with Machine Learning DOI Creative Commons
Seisuke Kano

Machines, Journal Year: 2025, Volume and Issue: 13(2), P. 81 - 81

Published: Jan. 23, 2025

Tribology plays a critical role in machining technologies. Friction is an essential factor processes such as composite material and bonding. This short review highlights the recent advancements controlling leveraging tribological phenomena machining. For instance, high-precision increasingly relying on situ observation real-time measurement of tools, test specimens, equipment for effective process control. Modern engineering materials often incorporate functional metastable states, composites dissimilar materials, rather than conventional stable-phase materials. In these cases, effects during can impede precision. On other hand, friction additive manufacturing demonstrates constructive application tribology. Traditionally, understanding mitigating have involved developing physical chemical models individual factors using simulations to inform decisions. However, accurately predicting system behavior has remained challenging due complex interactions between machine components variations initial operational (or deteriorated) states. Recent innovations introduced data-driven approaches that predict without need detailed models. By integrating advanced monitoring technologies learning, methods enable predictions within controllable parameters live data. shift opens new possibilities achieving more precise adaptive

Language: Английский

Citations

0
Prediction of mechanical properties of high entropy alloys based on machine learning DOI
Tinghong Gao, Qingqing Wu, Lei Chen

et al.

Physica Scripta, Journal Year: 2025, Volume and Issue: 100(4), P. 046013 - 046013

Published: March 5, 2025

Abstract In recent years, the ideal- properties (young’s modulus, yield strength, toughness) and advanced application potential of high-entropy alloys (HEAs) have attracted numerous researchers. However, due to their unique structure multiple structural combinations, it is challenging explore impact various factors on mechanical performance solely through experiments. This study considers concentrations five alloy atoms working temperature as input parameters. Molecular dynamics (MD) simulations machine learning (ML) algorithms are employed predict tensile FeNiCrCoCu HEAs, including Young’s modulus ( E ) toughness uT ). A dataset 1000 HEAs generated MD simulations, feature selection conducted using principal component analysis Spearman correlation analysis. XGBoost, RF, DT, LGBoost, AdaBoost utilized comparing two methods prediction outcomes. During ML model training, 10-fold cross-validation grid search obtain best models Root mean squard error RMSE ), coefficient determination R 2 absolute MAE relative RAE used evaluation metrics. Results indicate that for outperforms analysis, XGBoost demonstrates superior predictive compared other models. Predictions more accurate than those , with exceeding 0.9 four out work may provide a new method studying ML. future, this can be applied research areas compositions, providing theoretical support It then further critical fields such biomedical aerospace industries.

Language: Английский

Citations

0
Phase Stability and Transitions in High-Entropy Alloys: Insights from Lattice Gas Models, Computational Simulations, and Experimental Validation DOI Creative Commons
Łukasz Łach

Entropy, Journal Year: 2025, Volume and Issue: 27(5), P. 464 - 464

Published: April 25, 2025

High-entropy alloys (HEAs) are a novel class of metallic materials composed five or more principal elements in near-equimolar ratios. This unconventional composition leads to high configurational entropy, which promotes the formation solid solution phases with enhanced mechanical properties, thermal stability, and corrosion resistance. Phase stability plays critical role determining their structural integrity performance. study provides focused review HEA phase transitions, emphasizing lattice gas models predicting behavior. By integrating statistical mechanics thermodynamic principles, enable accurate modeling atomic interactions, segregation, order-disorder transformations. The combination computational simulations (e.g., Monte Carlo, molecular dynamics) experimental validation XRD, TEM, APT) improves predictive accuracy. Furthermore, advances data-driven methodologies facilitate high-throughput exploration compositions, accelerating discovery optimized superior Beyond applications, HEAs demonstrate potential functional domains, such as catalysis, hydrogen storage, energy technologies. brings together theoretical modeling—particularly approaches—and form unified understanding behavior high-entropy alloys. highlighting mechanisms behind transitions implications for material performance, this work aims support design optimization real-world applications aerospace, systems, engineering.

Language: Английский

Citations

0
Machine learning based prediction of Young's modulus of stainless steel coated with high entropy alloys DOI Creative Commons

N. Radhika,

M. Sabarinathan,

S. Ragunath

et al.

Results in Materials, Journal Year: 2024, Volume and Issue: 23, P. 100607 - 100607

Published: July 29, 2024

The High Entropy Alloy (HEA) coatings exhibit diverse properties contingent upon their composition and microstructure, addressing current industrial requirements. Machine Learning (ML) regression emerges as a proficient solution for predicting the of HEA coatings, offering significant reduction in experimental work. ML regressions including Support Vector Regression (SVR), Gaussian Process (GPR), Ridge (RR), Polynomial (PR), are effectively employed to predict Young's modulus coated Stainless Steel (SS) through database. statistical responses developed models analyzed evaluation indices Coefficient determination (R2), Mean Absolute Error (MAE), Root Square (RMSE). Among models, 2-degree PR model stands alone with high prediction accuracy R2-0.95, MAE-16.12, RMSE-21.53. demonstrates correlation between predicted modulus, contributing accurate unknown HEA-coated SS. by is more reliable, proved an error percentile ±4.76 %, compared values modulus.

Language: Английский

Citations

3
Recent machine learning-driven investigations into high entropy alloys: a comprehensive review DOI
Yonggang Yan, Xunxiang Hu,

Yalin Liao

et al.

Journal of Alloys and Compounds, Journal Year: 2024, Volume and Issue: unknown, P. 177823 - 177823

Published: Nov. 1, 2024

Language: Английский

Citations

3
High entropy alloys for hydrogen storage applications: A machine learning-based approach DOI Creative Commons

N. Radhika,

Madabhushi Siri Niketh,

U.V. Akhil

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102780 - 102780

Published: Aug. 29, 2024

Hydrogen is a clean energy carrier and has potential applications in storage, power generation, transportation. This study explores the efficient safe storage of hydrogen, particularly through solid-state methods using high entropy alloys (HEAs). HEAs have garnered attention for their versatility tailoring properties hydrogen storage. The integration Machine Learning (ML) designing offers an expedited approach, analyzing datasets predicting material to enhance capacity, kinetics, stability. Despite significant progress, acknowledges certain research limitations, its relatively narrow focus on applying ML One biggest challenges with complexity, which. necessitates larger develop accurate predictive models. Collecting existing HEA data techniques main objective. Using algorithms like support vector regression (SVR), K-nearest (KNN), random forest (RF), hydrogen-to-metal ratio (H/M) valence electron configuration (VEC) are accurately predicted. proposes formation, identifying 741 quaternary 631 quinary HEAs. These compositions newly proposed do not yet exist. Out these, 774 identified as candidates applications. Applying techniques, selection process more efficient, reducing dependency time-consuming experiments making it easier discover promising candidates.

Language: Английский

Citations

2