Impact of the Input Dataset Size on Accuracy of Reduced Order Models of Rubber-Metal Elements for Static Characteristics
Abstract
The work deals with the impact of the input dataset size on accuracy of reduced order models (ROM) of rubber-metal elements (RME) for static characteristics. First chapter describes the size and structure of the input dataset. Second chapter focuses on the process of the input dataset generation. Third chapter describes the generation process of ROM of RME with given neural network (NN) settings. Fourth chapter compares the static stiffnesses of generated ROM models with finite element method (FEM) models with corresponding shapes for input datasets with different sizes.
© 2026 Juraj Dobrovolný, Ján Danko, Martin Bernáth, Tomáš Milesich, Igor Kevický, Ľuboš Magdolen, published by Slovak University of Technology in Bratislava
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.