Phase prediction and experimental realisation of a new high entropy alloy using machine learning

Singh, Swati; Katiyar, Nirmal Kumar; Goel, Saurav; Joshi, Shrikrishna N.

doi:10.1038/s41598-023-31461-7

Cited by 23 publications

(6 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each decision tree is trained on a random subset of the training data and a random subset of the features, which helps to reduce overfitting and increase diversity. The final prediction is made by aggregating and averaging the predictions of all the decision trees 117 . The objective function of RF can be represented as where F ( x ) represents the final prediction made by the RF model on input data point x. N is the number of decision trees in the ensemble.…”

Section: Methodsmentioning

confidence: 99%

Data-driven analysis and prediction of stable phases for high-entropy alloy design

Peivaste,

Jossou,

Tiamiyu

2023

Sci Rep

View full text Add to dashboard Cite

High-entropy alloys (HEAs) represent a promising class of materials with exceptional structural and functional properties. However, their design and optimization pose challenges due to the large composition-phase space coupled with the complex and diverse nature of the phase formation dynamics. In this study, a data-driven approach that utilizes machine learning (ML) techniques to predict HEA phases and their composition-dependent phases is proposed. By employing a comprehensive dataset comprising 5692 experimental records encompassing 50 elements and 11 phase categories, we compare the performance of various ML models. Our analysis identifies the most influential features for accurate phase prediction. Furthermore, the class imbalance is addressed by employing data augmentation methods, raising the number of records to 1500 in each category, and ensuring a balanced representation of phase categories. The results show that XGBoost and Random Forest consistently outperform the other models, achieving 86% accuracy in predicting all phases. Additionally, this work provides an extensive analysis of HEA phase formers, showing the contributions of elements and features to the presence of specific phases. We also examine the impact of including different phases on ML model accuracy and feature significance. Notably, the findings underscore the need for ML model selection based on specific applications and desired predictions, as feature importance varies across models and phases. This study significantly advances the understanding of HEA phase formation, enabling targeted alloy design and fostering progress in the field of materials science.

show abstract

Section: Methodsmentioning

confidence: 99%

Data-driven analysis and prediction of stable phases for high-entropy alloy design

Peivaste,

Jossou,

Tiamiyu

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Panneerselvam 8 studied the low-temperature fracture toughness of heavy-section ductile iron containers with 150 mm wall thickness, and the results showed that an increase in pearlite content led to a decrease in fracture toughness. Singh 9 found that the fracture surface of heavy-section ductile iron has a special metal oxide film, which greatly reduced the fracture toughness and elongation of the material. The film was observed was due to the long cooling time, which is obviously different from ordinary ductile iron.…”

Section: Introductionmentioning

confidence: 99%

Prediction of heavy-section ductile iron fracture toughness based on machine learning

Song,

Zhang,

Zhang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The preparation process and composition design of heavy-section ductile iron are the key factors affecting its fracture toughness. These factors are challenging to address due to the long casting cycle, high cost and complex influencing factors of this type of iron. In this paper, 18 cubic physical simulation test blocks with 400 mm wall thickness were prepared by adjusting the C, Si and Mn contents in heavy-section ductile iron using a homemade physical simulation casting system. Four locations with different cooling rates were selected for each specimen, and 72 specimens with different compositions and cooling times of the heavy-section ductile iron were prepared. Six machine learning-based heavy-section ductile iron fracture toughness predictive models were constructed based on measured data with the C content, Si content, Mn content and cooling rate as input data and the fracture toughness as the output data. The experimental results showed that the constructed bagging model has high accuracy in predicting the fracture toughness of heavy-section ductile iron, with a coefficient of coefficient (R2) of 0.9990 and a root mean square error (RMSE) of 0.2373.

show abstract

“…To address this challenge, the development of computational techniques such as density functional theory (DFT), Calculations of Phase Diagrams (CALPHAD), empirical relations, and molecular dynamics are explored for optimizing the composition of HEAs to minimize the trial-and-error methods by numerous experiments [13][14][15]. However, the prediction of these techniques is constrained by their applicability to limited alloys and the time and resources required for more accuracy in predictions [16]. In this context, it is optimal to utilize Machine Learning (ML) methods which improve the accuracy and efficiency of the results, by reducing the complexity of the situations [17].…”

Section: Introductionmentioning

confidence: 99%

“…Similar to ML, Deep Learning (DL) has also proved to be an effective prediction method rooted in the datadriven approach [16,18]. Among the two methods, ML is mostly preferred for structured data, due to its exceptional ability to detect complex patterns.…”

Section: Introductionmentioning

confidence: 99%

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

Sivaraman,

Radhika

2024

Phys. Scr.

View full text Add to dashboard Cite

High-entropy alloys (HEAs) are increasingly renowned for their distinct microstructural compositions and exceptional properties. These HEAs are employed for surface modification as coatings exhibit phenomenal mechanical characteristics including wear and corrosion resistance which are extensively utilized in various industrial applications. However, assessing the wear behaviour of the HEA coatings through conventional methods remains challenging and time-consuming due to the complexity of the HEA structures. In this study, a novel methodology has been proposed for predicting the wear behaviour of HEA coatings using Machine Learning (ML) algorithms such as Support Vector Machine (SVM), Linear Regression (LR), Gaussian Process Regression (GPR), Least Absolute Shrinkage and Selection Operator (LASSO), Bagging Regression (BR), Gradient Boosting Regression Tree (GBRT), and Robust regressions (RR). The analysis integrates of 75 combinations of HEA coatings with processing parameters and wear test results from peer-reviewed journals for model training and validation. Among the ML models utilized, the GBRT model was found to be more effective in predicting wear rate and Coefficient of Friction (COF) with the highest correlation coefficient of R2 value of 0.95 ∼ 0.97 with minimal errors. The optimum model is used to predict the unknown wear properties of HEA coatings from the conducted experiments and validate the results, making ML a crucial resource for engineers in the materials sector.

show abstract

Phase prediction and experimental realisation of a new high entropy alloy using machine learning

Cited by 23 publications

References 70 publications

Data-driven analysis and prediction of stable phases for high-entropy alloy design

Data-driven analysis and prediction of stable phases for high-entropy alloy design

Prediction of heavy-section ductile iron fracture toughness based on machine learning

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

Contact Info

Product

Resources

About