Open AccessAutomotive rubber part design using machine learning
Author(s) -
Dávid Huri,
Tamás Mankovits
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/659/1/012022
Subject(s) - finite element method , support vector machine , natural rubber , automotive industry , computer science , nonlinear system , process (computing) , product design , engineering design process , product (mathematics) , design process , mathematical optimization , machine learning , mechanical engineering , engineering , mathematics , process engineering , structural engineering , materials science , composite material , process integration , physics , geometry , quantum mechanics , aerospace engineering , operating system
In rubber products design finite element analysis is a widely used technique. In many cases, the pre-defined operating conditions can be achieved by changing the geometric dimensions of the product which is the well-known iterative design method. Using more than one design parameter the number of possible combinations will increase significantly. The application of Support Vector Machine (SVM) can handle the large number of data in a special way and helps to find the optimal design parameters. In this paper an optimization process of a rubber jounce is presented using nonlinear finite element analysis and SVM.