Automotive rubber part design using machine learning

Abstract

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.