On the Possibility of Replacing Scheil-Gulliver Modeling with Machine Learning and Neural Network Models

Ziyu Li; He Tan; Lucia Lattanzi; Anders E.W. Jarfors; Per Jansson

doi:10.4028/p-m0SUsZ

Paper Titles

Evolution of Microstructure and Mechanical Properties of the Rheo-Diecast Mg-12Gd-3Y-1Zn-0.4Zr Alloy during Heat Treatment
p.127

Rheological Behavior in the Semisolid State of Al-Si-Cu Alloys Produced by ECAP
p.135

Numerical Simulations of the Squeeze Flow of Thixotropic Semisolid Slurries
p.141

Semi-Solid Deformation Behavior, Flow Stress Prediction and Deformed Microstructure of GH3536 Superalloy
p.147

On the Possibility of Replacing Scheil-Gulliver Modeling with Machine Learning and Neural Network Models
p.157

Rheological Modeling of 7075 Aluminum Alloy Semi-Solid Slurry and its Application in the Simulation of SEED Rheocasting Process
p.165

CALPHAD Optimization of the Composition of EN AC-46000 Secondary Alloys for Semi-Solid Casting Processes
p.171

Comparison of Rheological Models to Simulate Die Filling Process of A356 Semisolid Alloy
p.177

Thixomolding of Magnesium - Efficient Process Industrialization by Combining a Digital Twin and Systematic Casting Trials
p.183

HomeSolid State PhenomenaSolid State Phenomena Vol. 347On the Possibility of Replacing Scheil-Gulliver...

On the Possibility of Replacing Scheil-Gulliver Modeling with Machine Learning and Neural Network Models

Abstract:

Resource-efficient manufacturing is a foundation for sustainable and circular manufacturing. Semi-solid processing typically reduces material loss and improves productivity but generally requires a better understanding and control of the solidification of the cast material. Thermal analysis is commonly used in high-pressure die casting (HPDC) processes to determine casting process parameters, such as liquidus and solidus temperatures. However, this method is inadequate for semi-solid casting processes because the eutectic temperature is also a crucial parameter for successful semi-solid casting. This study explores the feasibility of using machine learning and artificial neural networks to predict fundamental values in Al-Si alloy casting. The Thermo-Calc 2022 software Scheil-Gulliver calculation function was used to generate the training and the test datasets, which included features such as melting temperature, alpha aluminium solidification temperature, eutectic temperature, and the solid fraction amounts at eutectic temperature. The results show that both models have a symmetric mean absolute percentage error (SMAPE) of less than 2 % with temperature prediction, with the machine learning model achieving a better accuracy of less than 1 %. A case study comparing practical measurements with prediction results is also discussed, demonstrating the potential of AI methods for predicting semi-solid casting processes.

You might also be interested in these eBooks

Semi-Solid Processing of Alloys and Composites (S2P)

View Preview

Semi-Solid Casting of Structural Materials

View Preview

Info:

Periodical:

Solid State Phenomena (Volume 347)

Pages:

157-163

DOI:

https://doi.org/10.4028/p-m0SUsZ

Citation:

Cite this paper

Online since:

August 2023

Authors:

Ziyu Li, He Tan, Lucia Lattanzi, Anders E.W. Jarfors*, Per Jansson

Keywords:

Aluminum, Machine Learning, Neural Network, Segregation, Semi-Solid Casting, Solidification, Training Data Collection

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] Kirkwood, D.H. Semisolid Metal Processing. International Materials Reviews 1994, 39, 173–189.

DOI: 10.1179/imr.1994.39.5.173

Google Scholar

[2] Jarfors, A.E.W.; Jafari, M.; Aqeel, M.; Liljeqvist, P.; Jansson, P. In-Production Rheometry of Semi-Solid Metal Slurries. Metals 2022, Vol. 12, Page 1221 2022, 12, 1221.

DOI: 10.3390/MET12071221

Google Scholar

[3] Rebala, G.; Ravi, A.; Churiwala, S. Machine Learning Definition and Basics. An Introduction to Machine Learning 2019, 1–17.

DOI: 10.1007/978-3-030-15729-6_1

Google Scholar

[4] Malekian, A.; Chitsaz, N. Concepts, Procedures, and Applications of Artificial Neural Network Models in Streamflow Forecasting. Advances in Streamflow Forecasting 2021, 115–147.

DOI: 10.1016/B978-0-12-820673-7.00003-2

Google Scholar

[5] Puncreobutr, C.; Lohwongwatana, B.; Chongstitvattana, P. Genetic Programming Approach to Determining Thermal Properties of Lead-Free Solder Alloys (accessed on 7 July 2022).

Google Scholar

[6] Gao, J.; Zhong, J.; Liu, G.; Yang, S.; Song, B.; Zhang, L.; Liu, Z. A Machine Learning Accelerated Distributed Task Management System (Malac-Distmas) and Its Application in High-Throughput CALPHAD Computation Aiming at Efficient Alloy Design. Advanced Powder Materials 2022, 1, 100005.

DOI: 10.1016/J.APMATE.2021.09.005

Google Scholar

[7] Aluminum-Based Alloys - Thermo-Calc Software Available online: https://thermocalc.com/products/databases/aluminum-based-alloys/ (accessed on 13 February 2023).

Google Scholar

[8] Freeman, E.A.; Moisen, G.G.; Coulston, J.W.; Wilson, B.T. Random Forests and Stochastic Gradient Boosting for Predicting Tree Canopy Cover: Comparing Tuning Processes and Model Performance. Canadian Journal of Forest Research 2015, 46, 323–339.

DOI: 10.1139/cjfr-2014-0562

Google Scholar

[9] Yao, S.; Kronenburg, A.; Shamooni, A.; Stein, O.T.; Zhang, W. Gradient Boosted Decision Trees for Combustion Chemistry Integration. Applications in Energy and Combustion Science 2022, 11, 100077.

DOI: 10.1016/J.JAECS.2022.100077

Google Scholar

[10] Torgo, L.; Gama, J. Regression Using Classification Algorithms.

Google Scholar

[11] Berrar, D. Cross-Validation. In Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics; Elsevier, 2018; Vol. 1–3, p.542–545 ISBN 9780128114322.

DOI: 10.1016/b978-0-12-809633-8.20349-x

Google Scholar

[12] Tofallis, C. A Better Measure of Relative Prediction Accuracy for Model Selection and Model Estimation. Journal of the Operational Research Society 2015, 66, 1352–1362.

DOI: 10.1057/jors.2014.103

Google Scholar