Study on Process Parameters of Centrifugal Cast Al17 wt% Si and Predicting the Mechanical and Tribological Properties using Machine Learning Algorithms
DOI:
https://doi.org/10.18311/jmmf/2023/34490Keywords:
Al17wt%Si, Mechanical properties, Tribological properties, Prediction models, Machine learning algorithmAbstract
Aluminum alloys are the most widely utilized metal in today’s world for manufacturing all industrial applications that
demand lightweight characteristics as well as mechanical and tribological capabilities. As a requirement for obtaining
quality products, it is critical that the manufacturing process is also optimized. As a replace to the conventional methods
of manufacturing, this article presents the development of machine learning (ML) models for Al-17wt% Si taking into
account process parameters such as different teeming temperatures and rotation speeds of molds. In addition, the properties
of hardness and wear are taken into account in the construction of the data base and the models are formed for the same.
In this work, machine learning techniques such as Linear Regression (LR) and Artificial Neural Networks (ANN) algorithms
are used to predict tensile and wear properties. ANN and LR models show similar results, but ANN can handle many more
complexities, making the model reliable. This method of predicting the properties will lead to the definition of the optimized
process parameters, minimizing the efforts on conventional manufacturing and testing processes.
Downloads
Metrics
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
M Aruna Devi, C P S Prakash, et al, (2020): “An Informatic Approach to Predict the Mechanical Properties of Aluminum Alloys Using Machine Learning Techniques” Proceedings of the International Conference on Smart Electronics and Communication (ICOSEC 2020) IEEE Xplore Part Number: CFP20V90- ART; ISBN: 978-1-7281-5461-9 pp 536-541
Santos, Igor & Nieves, J. & Penya, Y.K. & Bringas, Pablo, (2009): “Machine-learning-based mechanical properties prediction in foundry production” ICCASSICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings, pp 4536 - 4541.
Shankar, H. (2020, May): Study and development of aluminium metal matrix composite with SiC using stir casting process. In AIP conference proceedings (Vol. 2236, No.1, p. 040003). AIP Publishing LLC.
Cristiano Fragassa, Matej Babic, Carlos Perez Bergmann and Giangiacomo Minak (2019): “Predicting the Tensile Behaviour of Cast Alloys by a Pattern Recognition Analysis on Experimental Data” Metals 2019, 9, 557 PP 1-21
David Merayo, Alvaro Rodríguez-Prieto and Ana María Camacho (2020): “Prediction of Mechanical Properties by Artificial Neural Networks to Characterize the Plastic Behaviour of Aluminum Alloys” Materials 2020, 13, 5227; doi:10.3390/ ma13225227 pp 1-22
Hamritha, S., Shilpa, M., Shivakumar, M. R., Madhoo, G., & Harshini, Y. P. (2021): Study of Mechanical and Tribological Behaviour of Aluminium Metal Matrix Composite Reinforced with Alumina. In Materials Science Forum, Vol. 1019, pp. 44-50. Trans Tech Publications Ltd.
R. Soundararajan, A. Ramesh, S. Sivasankaran and A. Sathishkumar (2015): “Modelling and Analysis of Mechanical Properties of Aluminum Alloy (A413) Processed through Squeeze Casting Route Using Artificial Neural Network Model and Statistical Technique” Advances in Materials Science and Engineering, Volume 2015, Article ID 714762, PP 1-17
Akshansh Mishra (2020): “Artificial Intelligence Algorithms for the Analysis of Mechanical Property of Friction Stir Welded Joints by using Python Programming” Welding Technology Review, Vol. 92(6) 2020 pp 6-16
Bonollo, Franco & Moret, A. & Gallo, S. & Mus, Cherry. (2004): Cilinder liners in aluminium matrix composite by centrifugal casting. Metallurgia Italiana. 96. 49-55.x
Harish, N. & Hamritha, S. & Aithal, Kiran. (2015): Characterization of Al-17wt.%Si Using Centrifugal Casting. Applied Mechanics and Materials. 766-767. 399-404. 10.4028/www.scientific.net/AMM.766-767