Parameter Optimization of Rubber Mounts Based on Finite Element Analysis and Genetic Neural Network

Abstract

The structures of vehicle rubber mounts cannot be optimized with conventional optimization methods due to their complex structures and irregular sections. A parameter optimization methodology for a rubber mount based on Finite Element Analysis (FEA) and Genetic Neural Network models is proposed in this study. A FEA model of the rubber mount was developed and analyzed using the software MSC.MARC, and the primary stiffness of rubber mounts with different geometric parameters in three principle directions were obtained by this FEA method. Then the FEA results were used as samples to train the neural network (NN) model which defines the non-linear global mapping relationship between the rubber mount's geometric parameters and its primary stiffness in three principle directions. The fitness values of the population in the genetic algorithm (GA) were calculated by the trained NN model and the optimal solution was acquired with the mutation of population. Finally, experiments were made to validate the reliability of the optimal solution. The proposed optimization method can shorten the product design cycle and decrease the design and trial-product cost considerably.