DETERMINATION OF THE RELATIVE MAGNETIC PERMEABILITY BY USING AN ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM AND 2D-FEM

Adaptive Neuro-fuzzy systems constitute an intelligent systems hybrid technique that combines fuzzy logic with neural networks in order to have better results. A study is presented to forecast the relative magnetic permeability using ANFIS. The global electromagnetic parameter, namely, the magnetic induction has been used as input to estimate the relative magnetic permeability. In this exceptional research, flnite element simulations are carried out to build up a database which will be used to train ANFIS network. The ANFIS approach learns the rules and membership functions from training data. The hybrid system is tested by the use of the validation data. Performance of the trained ANFIS network was compared with the multilayer feed forward network model and experimental results. The results show the efiectiveness of the proposed approach in solving inverse electromagnetic problem.