volume | PIER Journals

Abstract

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, finite 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 effectiveness of the proposed approach in solving inverse electromagnetic problem.

1. Liu, G. R. and X. Han, Computational Inverse Techniques in Nondestructive Evaluation, CRC Press, 2003.
doi:10.1201/9780203494486

2. Jang, J. S. R. and C. T. Sun, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice Hall, 1997.

3. Jang, J. R., "ANFIS: Adaptive-network-based fuzzy inference systems," IEEE Transactions on Systems, Man and Cybernetics (IEEE), Vol. 23, No. 3, 2889-2892, May 1993. Google Scholar

4. Fouladgar, J., "The inverse problem methodology for the measurement of the permeability of the ferromagnetic materials," IEEE Transactions on Magnetics, Vol. 33, No. 2, 2889-2892, March 1997.
doi:10.1109/20.582754 Google Scholar

5. Mamdani, E. H., "Applications of fuzzy logic to approximate reasoning using linguistic synthesis," IEEE Transactions on Computers, Vol. 26, No. 12, 1182-1191, 1977.
doi:10.1109/TC.1977.1674779 Google Scholar

6. Nagata, S., M. Enokizono, T. Chady, and R. Sikora, Low Frequency Excitation of MFES, Electromagnetic Nondestructive Evaluation (VIII), IOS-Press, 2004.

7. Silvester, P. P. and R. L. Ferrari, Finite Elements for Electrical Engineers, Univ Press, 1996.

8. Matlab, , PDE Toolbox User's Guide, www.mathworks.com.

9. Hacib, T., M. R. Mekideche, N. Ferkha, N. Ikhlef, and H. Bouridah, "Application of a radial basis function neural network for the inverse electromagnetic problem of parameter identification," The First IEEE International Symposium on Industrial Electronicss, ISIE 2007, Vigo, Spain, June15-18, 2007. Google Scholar

10. Hacib, T., M. R. Mekideche, and N. Ferkha, "Defect identification using artificial neural networks and finite element method," International Conference on E-learning in Industrial Electronics, ICEIE 2007, Hammamet, Tunisia, December 10-12, 2007. Google Scholar

11. Matlab, , Fuzzy Logic Toolbox User's Guide, www.mathworks.com.

12. Low, T. S. and B. Chao, "The use of finite elements and neural networks for the solution of inverse electromagnetic problems," IEEE Transactions on Magnetics, Vol. 28, No. 5, 1931-1934, 1992.
doi:10.1109/20.179635 Google Scholar

13. De Alcantara, N. P., J. Alexandre, and M. de Carvalho, "Computational investigation on the use of FEM and ANN in the non-destructive the analysis of metallic tubes," the Biennial Conference on Electromagnetic Field Computationn, BCEFC 2002, Rome, Italy, June 12-14, 2002. Google Scholar

14. Matlab, , Neural Network Toolbox User's Guide, www.mathworks.com.

Dr. Naamane Mohdeb

Dr. Mohamed Rachid Mekideche