Interpretable hardness prediction of high-entropy alloys through ensemble learning

Journal of Alloys and Compounds, Journal Year: 2023, Volume and Issue: 945, P. 169329 - 169329

Published: Feb. 16, 2023

Language: Английский

---

A neural network model for high entropy alloy design

npj Computational Materials, Journal Year: 2023, Volume and Issue: 9(1)

Published: April 12, 2023

Abstract A neural network model is developed to search vast compositional space of high entropy alloys (HEAs). The predicts the mechanical properties HEAs better than several other models. It’s because special structure helps understand characteristics constituent elements HEAs. In addition, thermodynamics descriptors were utilized as input so that by understanding thermodynamic conditional random search, which good at finding local optimal values, was selected inverse predictor and designed two using model. We experimentally verified have best combination strength ductility this proves validity alloy design method. strengthening mechanism further discussed based on microstructure lattice distortion effect. present approach, specialized in multiple optima, could help researchers an infinite number new with interesting properties.

Language: Английский

---

Machine Learning Paves the Way for High Entropy Compounds Exploration: Challenges, Progress, and Outlook

Advanced Materials, Journal Year: 2023, Volume and Issue: unknown

Published: Sept. 9, 2023

Abstract Machine learning (ML) has emerged as a powerful tool in the research field of high entropy compounds (HECs), which have gained worldwide attention due to their vast compositional space and abundant regulatability. However, complex structure HEC poses challenges traditional experimental computational approaches, necessitating adoption machine learning. Microscopically, can model Hamiltonian system, enabling atomic‐level property investigations, while macroscopically, it analyze macroscopic material characteristics such hardness, melting point, ductility. Various algorithms, both methods deep neural networks, be employed research. Comprehensive accurate data collection, feature engineering, training selection through cross‐validation are crucial for establishing excellent ML models. also holds promise analyzing phase structures stability, constructing potentials simulations, facilitating design functional materials. Although some domains, magnetic device materials, still require further exploration, learning's potential is substantial. Consequently, become an indispensable understanding exploiting capabilities HEC, serving foundation new paradigm Artificial‐intelligence‐assisted exploration.

Language: Английский

---

Prediction of the yield strength of as-cast alloys using the random forest algorithm

Materials Today Communications, Journal Year: 2024, Volume and Issue: 38, P. 108520 - 108520

Published: March 1, 2024

Language: Английский

---

Data-driven design of novel lightweight refractory high-entropy alloys with superb hardness and corrosion resistance

npj Computational Materials, Journal Year: 2024, Volume and Issue: 10(1)

Published: Nov. 13, 2024

Abstract Lightweight refractory high-entropy alloys (LW-RHEAs) hold significant potential in the fields of aviation, aerospace, and nuclear energy due to their low density, high strength, hardness, corrosion resistance. However, enormous composition space has severely hindered development novel LW-RHEAs with excellent comprehensive performance. In this paper, an machine learning (ML)-based alloy design strategy combined a multi-objective optimization method was proposed applied for rational Al-Nb-Ti-V-Zr-Cr-Mo-Hf LW-RHEAs. The quantitative relation “composition-structure-property” first established by ML modeling. Then, feature analysis reveals that Cr content greater than 12 at.% is key criterion phase structure, melting point, hardness resistance were screened layer layer, finally, three superb hard successfully designed. Key experimental validation indicates target have densities around 6.5 g/cm 3 , all are disordered bcc_A2 single-phase highest 593 HV largest pitting 2.5 V SCE which far exceeds literature reports. successful demonstration paper clearly demonstrates present driven technique should be generally applicable other RHEA systems.

Language: Английский

---

Prediction and design of high hardness high entropy alloy through machine learning

Materials & Design, Journal Year: 2023, Volume and Issue: 235, P. 112454 - 112454

Published: Nov. 1, 2023

Two data-driven machine learning (ML) models were proposed for the hardness prediction of high-entropy alloys (HEA) and composition optimization high HEAs, respectively. The model combined interpretable ML methods with solid solution strengthening theory, R2 RMSE values 0.9716 39.2525 respectively achieved under leave-one-out validation method. adopted an intelligent algorithm to design optimized elemental molar ratios HEAs was experimentally verified. A general framework summarized various HEA performances.

Language: Английский

---

Data-driven design of high bulk modulus high entropy alloys using machine learning

Journal of Alloys and Metallurgical Systems, Journal Year: 2024, Volume and Issue: 8, P. 100128 - 100128

Published: Nov. 15, 2024

Language: Английский

---

Predictive analytics of wear performance in high entropy alloy coatings through machine learning

Physica Scripta, Journal Year: 2024, Volume and Issue: 99(7), P. 076014 - 076014

Published: June 10, 2024

Abstract High-entropy alloys (HEAs) are increasingly renowned for their distinct microstructural compositions and exceptional properties. These HEAs employed surface modification as coatings exhibit phenomenal mechanical characteristics including wear corrosion resistance which extensively utilized in various industrial applications. However, assessing the behaviour of HEA through conventional methods remains challenging time-consuming due to complexity structures. In this study, a novel methodology has been proposed predicting using Machine Learning (ML) algorithms such Support Vector (SVM), Linear Regression (LR), Gaussian Process (GPR), Least Absolute Shrinkage Selection Operator (LASSO), Bagging (BR), Gradient Boosting Tree (GBRT), Robust regressions (RR). The analysis integrates 75 combinations with processing parameters test results from peer-reviewed journals model training validation. Among ML models utilized, GBRT was found be more effective rate Coefficient Friction (COF) highest correlation coefficient R 2 value 0.95 ∼ 0.97 minimal errors. optimum is used predict unknown properties conducted experiments validate results, making crucial resource engineers materials sector.

Language: Английский

---

Unraveling dislocation-based strengthening in refractory multi-principal element alloys

npj Computational Materials, Journal Year: 2024, Volume and Issue: 10(1)

Published: July 2, 2024

Abstract Refractory multi-principal element alloys (RMPEAs) draw great interest with their superior mechanical properties and extremely high melting points, yet the strengthening mechanism remains unclear. Here, we calculate critical resolved shear stress (CRSS) for a single dislocation to move in RMPEAs consisting of 4 or 5 elements without short-range order (SRO) represent strength by machine learning-based interatomic potential. The increased CRSS is then attributed lattice distortion, elastic mismatch, SRO strengthening, all which originate from solid solution theory. After detailed research across many systems different composition ratios, construct an XGBoost model predict few parameters rank importance. We find that distortion strongly influences both types reduces screw-to-edge ratio CRSS, while mismatch has more significant impact on screw than edge one.

Language: Английский

---

Machine learning-assisted design of high-entropy alloys with superior mechanical properties

Journal of Materials Research and Technology, Journal Year: 2024, Volume and Issue: 33, P. 260 - 286

Published: Sept. 6, 2024

Language: Английский

---