Evaluation of Machine Learning Models for Predicting the Hot Deformation Flow Stress of Sintered Al–Zn–Mg Alloy
Source abstract
Abstract
Abstract In predicting flow stress, machine learning (ML) offers significant advantages by leveraging data-driven approaches, enhancing material design, and accurately forecasting material performance. Thus, the present study employs various supervised ML models, including linear regression (Lasso and Ridge), support vector regression (SVR), ensemble methods (random forest (RF), gradient boosting (GB), extreme gradient boosting (XGB)), and neural networks (artificial neural network (ANN), multilayer perceptron (MLP)), to predict flow stress in the hot deformation of an Al–Zn–Mg alloy. The ML methodology involves sequential steps from data extraction to cross-validation and hyperparameter tuning, which is conducted using the hyperopt library. Model performance is assessed using average absolute relative error (AARE), root-mean-squared error (RMSE), and mean squared error (MSE). The results show that ensemble methods (RF, GB, XGB) and neural networks outperform traditional regression methods, demonstrating superior predictive accuracy. Visualization using half-violin plots reveals the models' error ranges, with XGB consistently exhibiting the best performance. SVR, RF, GB, XGB, ANN, and MLP showed better performance than the Arrhenius model in the context of AARE and MSE metrics. Interestingly, SVR had a somewhat higher AARE of 1.89% and an MSE of 0.251 MPa2, while XGB had the lowest AARE of 0.2% and the lowest MSE of 0.011 MPa2. When ML models were evaluated using the skill score in relation to the Arrhenius model, XGB scored higher than the support vector machine (SVM) at 0.714, with a score of 0.986. In contrast, Lasso and Ridge exhibited negative scores of −0.847 and −0.456, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Powder Metallurgy Techniques and Materials · Metallurgy and Material Forming · Injection Molding Process and Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shri Vishnu Engineering College for Women Department of Mechanical Engineering, , Bhimavaram 534202 , ;
National Institute of Technology Department of Mechanical Engineering, , Warangal 506004 ,
Sreenidhi Institute of Science and Technology Department of Mechanical Engineering, , Hyderabad 501301 ,
References (40)
Show source-provided references
1. Dynamic Tensile Deformation of High Strength Aluminum Alloys Processed Following Novel Thermomechanical Treatment Strategies10.1002/adem.202000193 ↗
2. Recent Development in Aluminium for Automotive Applications10.1016/S1003-6326(14)63305-7 ↗
3. Modeling the High-Temperature Creep Behaviors of 7075 and 2124 Aluminum Alloys by Continuum Damage Mechanics Model10.1016/j.commatsci.2013.02.022 ↗
4. Study of the Constitutive Behavior of 7075-T651 Aluminum Alloy10.1016/j.ijimpeng.2017.05.002 ↗
5. Investigating the Effects of Deformation-Induced Densification on the Constitutive Behavior and Corrosion Resistance of Al–Zn–Mg Powder Metallurgy Alloy During hot Deformation10.1177/14644207231207820 ↗
6. Role of Pre-Strain on the Corrosion Behaviour of Al-Zn-Mg P/M Alloy10.1177/14644207221109676 ↗
7. Hot Compressive Deformation Behavior of 7075 Al Alloy Under Elevated Temperature10.1007/s10853-011-5904-y ↗
8. Constitutive Analysis in Hot Working10.1016/S0921-5093(01)01117-0 ↗
9. Constitutive Modeling of Flow Behavior and Microstructure Evolution of AA7075 in Hot Tensile Deformation10.1016/j.msea.2017.12.028 ↗
10. Overcoming Optical Image Challenges in Automatic Grain Size Measurement Using a Novel Computer Vision Algorithm Applied to Hot Deformation of Al-Zn-Mg Powder Metallurgy Alloy10.1016/j.matlet.2023.135743 ↗
11. New Method for Microstructure Segmentation and Automatic Grain Size Determination Using Computer Vision Technology During the Hot Deformation of an Al-Zn-Mg Powder Metallurgy Alloy10.1007/s11665-023-09025-7 ↗
12. Artificial Neural Network Modeling to Predict the Hot Deformation Behavior of an A356 Aluminum Alloy10.1016/j.matdes.2012.12.082 ↗
13. Constitutive Modeling of the Hot Deformation Behavior in 6082 Aluminum Alloy10.1007/s11665-019-3873-5 ↗
14. A Simple Zerilli-Armstrong Constitutive Equation for Modeling and Prediction of Hot Deformation Flow Stress of Steels10.1016/j.mechmat.2015.11.013 ↗
15. Dislocation Mechanics-Based Constitutive Equations10.1007/s11661-004-0201-x ↗
16. Dynamic Recrystallization Mechanisms of as-Forged Al–Zn–Mg-(Cu) Aluminum Alloy During Hot Compression Deformation10.1016/j.msea.2023.145236 ↗
17. Application of Neural Networks to Predict the Elevated Temperature Flow Behavior of a Low Alloy Steel10.1016/j.commatsci.2008.01.039 ↗
18. A Comparative Study of Constitutive Models for Flow Stress Behavior of Medium Carbon Cr-Ni-Mo Alloyed Steel at Elevated Temperature10.1557/jmr.2017.356 ↗
19. Hardness Prediction in the Upsetting Process of Al%ZrO2—An Approach to Machine Learning Using Regression and Classification Models10.1139/tcsme-2023-0063 ↗
20. Integrating Data Mining and Machine Learning to Discover High-Strength Ductile Titanium Alloys10.1016/j.actamat.2020.10.056 ↗
21. Mechanical Properties Prediction of Superalloy FGH4095 Treated by Laser Shock Processing Based on Machine Learning10.1016/j.matlet.2021.129970 ↗
22. Shallow and Deep Learning of an Artificial Neural Network Model Describing a Hot Flow Stress Evolution: A Comparative Study10.1016/j.matdes.2022.110880 ↗
23. Machine Learning Model Predict Stress-Strain Plot for Marlow Hyperelastic Material Design10.1016/j.mtcomm.2021.102213 ↗
24. Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods10.3390/cryst12091281 ↗
25. Application of Machine Learning Methods for the Prediction of Roll Force and Torque During Plate Rolling of Micro-Alloyed Steel10.1016/j.jalmes.2023.100044 ↗
26. Comparison and Error Evaluation of Arrhenius Model and Typical Machine Learning Algorithms for High-Temperature Flow Stress Prediction of GH3536 Superalloy10.1016/j.matlet.2023.134754 ↗
27. Characteristics of Work Hardening and Constitutive Models Comparison of Powder Metallurgy Al-5.6Zn-2Mg Alloy During Hot Compression10.1007/s11771-024-5568-9 ↗
28. Unravelling the Hot Working Behavior, Constitutive Modeling, and Processing Map for Controlling the Microstructure of Sintered Al–Zn–Mg Alloy10.1007/s13369-023-08633-8 ↗
29. Evaluation of Constitutive Equations for Modeling and Characterization of Microstructure During Hot Deformation of Sintered Al–Zn–Mg Alloy10.1016/j.jmrt.2023.12.050 ↗
30. Influence of Incremental Pre-Strain on Corrosion Behavior of Al-Zn-Mg Powder Metallurgy Alloy During Hot Forging10.1177/09544062221143001 ↗
31. A Critical Review of Experimental Results and Constitutive Descriptions for Metals and Alloys in Hot Working10.1016/j.matdes.2010.11.048 ↗
32. Hot Workability10.1179/095066072790137765 ↗
33. Effect of Strain Rate Upon Plastic Flow of Steel10.1063/1.1707363 ↗
34. Constitutive Modeling of Powder Metallurgy Processed Al-4%Cu Preforms During Compression at Elevated Temperature10.1016/j.matdes.2014.08.069 ↗
35. Mathematical Models to Predict Flow Stress and Dynamically Recrystallized Grain Size of Deformed AA7150-5 wt% B4C Composite Fabricated Using Ultrasonic-Probe Assisted Stir Casting Process10.1007/s12540-021-00967-y ↗
36. Hot Tensile Deformation Behaviors and Constitutive Model of an Al-Zn-Mg-Cu Alloy10.1016/j.matdes.2014.02.052 ↗
37. Discontinuous Dynamic Recrystallization and Nucleation Mechanisms Associated With 2-, 3- and 4-Grain Junctions of Polycrystalline Nickel-Based Superalloys10.1016/j.matdes.2023.112041 ↗
38. An Investigation Into the Hot Deformation Characteristics of 7075 Aluminum Alloy10.1016/j.matdes.2010.12.047 ↗
39. ANN Constitutive Model for High Strain-Rate Deformation of Al 7075-T610.1016/j.jmatprotec.2006.11.228 ↗
40. Comparative Study of Phenomenological Constitutive Equations for an as-Rolled M50NiL Steel During Hot Deformation10.1016/j.jallcom.2016.11.131 ↗