Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube
Mohamed ElShazly, M., Osman, T., Shazly, M. (2020). Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube. EKB Journal Management System, 2(4), 91-100. doi: 10.21608/jisse.2020.49710.1034
Moataz Abdelgawad Mohamed ElShazly; Tarek Osman; Mostafa Shazly. "Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube". EKB Journal Management System, 2, 4, 2020, 91-100. doi: 10.21608/jisse.2020.49710.1034
Mohamed ElShazly, M., Osman, T., Shazly, M. (2020). 'Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube', EKB Journal Management System, 2(4), pp. 91-100. doi: 10.21608/jisse.2020.49710.1034
Mohamed ElShazly, M., Osman, T., Shazly, M. Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube. EKB Journal Management System, 2020; 2(4): 91-100. doi: 10.21608/jisse.2020.49710.1034

Development of a Mathematical Model Using Machine Learning for Hydroforming of Non-Circular Protrusion Copper T-Tube

Journal of International Society for Science and Engineering
Article 3, Volume 2, Issue 4, December 2020, Page 91-100  XML PDF (451.77 K)
Document Type: Original Article
DOI: 10.21608/jisse.2020.49710.1034
View on SCiNiTO View on SCiNiTO
Authors
Moataz Abdelgawad Mohamed ElShazly email 1; Tarek Osman2; Mostafa Shazly3
1M.Sc. (Honor), Mechanical Design and Production Department, Faculty of Engineering, Cairo University, Egypt
2Professor of Machine Design, Faculty of Engineering, Cairo University
3Professor of Solid Mechanics, The British University in Egypt, Al-Sherouk City, Cairo-Suez Desert Road, 11837, Cairo, EGYPT
Abstract
Optimum loading paths for successful tube hydroforming processes have been studied by several researchers. In this paper, an adaptive, heuristic, nonlinear mathematical model (AHNM) was proposed to optimize the loading path of a hydroforming process through adaptive minimization of the internal pressure and axial load of the process. Firstly, Finite Element Analysis (FEA) was used to analyze the hydroforming process where several features of the process were extracted from the FEA for further analyses of the relations among them. To capture these relations and include them in the AHNM, the paper examined several Machine Learning algorithms including Multiple Linear Regression, Multiple Ridge Regression, Decision Tree, and Random Forest. The Multiple Ridge Regression was found to give the highest accuracy to efficiently linear modelling the inputs and outputs of the FEA of the hydroforming process. The AHNM model was implemented, solved, and optimized using several steps of tee protrusion height that create several loading paths. It was found that increasing the number of steps and starting with small increment leads to minimizing the system requirements.
Keywords
Tube hydroforming; machine learning; multiple ridge regression; loading path; wrinkling
Statistics
Article View: 287
PDF Download: 214