ANFIS Networks Design using Hybrid Gentic and SVD Methods for Modelling of Rubbdr Engine Mount Stiffness

Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed for optimal design of both Gaussian membership functions of antecedents and vector of linear coefficients of consequents, respectively, of ANFIS networks which are used for modelling of stiffness of rubber engine mount. The aim of such modelling is to show how the stiffness of an engine mount varies with the variation of geometric parameters. It is demonstrated that SVD can be effectively used to optimally find the vector of linear coefficients of conclusion parts in ANFIS (Adaptive Neuro-Fuzzy Inference Systems) models whilst their Gaussian membership functions in premise parts are determined by GA. In this way, the stiffness training data are obtained for 36 different bush type engine mounts by using the finite element analysis (FEA).

Keywords:

ANFIS , Engine Mount , Genetic Algorithms (GAs) , SVD , FEA