volume | PIER Journals

2010-08-02

Artificial Neural Networks Approach in Microwave Filter Tuning

Jerzy Julian Michalski

Dr. Jerzy Julian Michalski

TeleMobile Electronics Ltd.

Poland

Homepage

Progress In Electromagnetics Research M, Vol. 13, 173-188, 2010

doi:10.2528/PIERM10053105 | Google Scholar

Abstract

This paper presents a novel method of cavity filter tuning with the usage of an artificial neural network (ANN). The proposed method does not require information on the filter topology, and the filter is treated as a black box. In order to illustrate the concept, a feed-forward, multi-layer, non-linear artificial neural network with back propagation is applied. The method for preparing, learning and testing vectors consisting of sampled detuned scattering characteristics and corresponding tuning screw deviations is proposed. To collect the training vectors, the machine, an intelligent automatic filter tuning tool integrated with a vector network analyzer, has been built. The ANN was trained on the basis of samples obtained from a properly tuned filter. It has been proved that the usage of multidimensional approximation ability of an ANN makes it possible to map the characteristic of a detuned filter reflection in individual screw errors. Finally, after the ANN learning process, the tuning experiment on 6 and 11-cavity filters has been preformed, proving a very high efficiency of the presented method.

Download Full Article (1863) View Full Article volume

Citation

Copy Export

Jerzy Julian Michalski, "Artificial Neural Networks Approach in Microwave Filter Tuning," Progress In Electromagnetics Research M, Vol. 13, 173-188, 2010.
doi:10.2528/PIERM10053105

References

1. Simplified filter tuning using time domain, , HP Application, Santa Rosa, CA, Note 1287-8, 1999.
doi:10.1109/22.20035

2. Mirzai, A. R., C. F. N. Cowan, and T. M. Crawford, "Intelligent alignment of waveguide filters using a machine learning approach," IEEE Trans. Microwave Theory & Tech., Vol. 37, No. 1, 166-173, January 1989.
doi:10.1109/22.963147 Google Scholar

3. Harscher, P. and R. Vahldieck, "Automated computer-controlled tuning of waveguide filters using adaptive network models," IEEE Trans. Microwave Theory & Tech., Vol. 49, No. 11, 2125-2130, November 2001.
doi:10.1109/TMTT.2002.805291 Google Scholar

4. Miraftab, V. and R. R. Mansour, "Computer-aided tuning of microwave filters using fuzzy logic," IEEE Trans. Microwave Theory & Tech., Vol. 50, No. 12, 2781-2788, December 2002. Google Scholar

5. Cegielski, T. and J. Michalski, "Heuristic methods for automated microwave filter tuning," Proceedings of XVII International Conference on Microwave, Radar and Wireless Communications MIKON-2008, Vol. 3, 647-650, Poland, Wroclaw, May 19-21, 2008.
doi:10.1007/BF03037088 Google Scholar

6. Amari, S. L., "Mathematical theory of neural learning," New Generation Computing, Vol. 8, 281-294, 1991.
doi:10.1016/0893-6080(89)90020-8 Google Scholar

7. Hornik, K., M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, Vol. 2, 359-366, 1989. Google Scholar

8. Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper Ssaddle River, NJ, 1999.
doi:10.1137/1116025

9. Vapnik, V. N. and A. Chervonenkis, "On the uniform convergence of relative frequencies of events to their probabilities," Theory of Probability Appl., Vol. 16, 264-280, 1971. Google Scholar

10., Intelligent automatic filter tuning tool (IAFTT) is registered with Priority certificate #2516" (Hannover Cebit 2007), and patent pending European Patent Application No. P382895 assigned by Polish National Patent Office". More information on www.trimsoluti.

11. Yu, M. and W. C. Tang, "A fully automated filter tuning robots for wireless base station diplexers, workshop computer aided filter tuning," IEEE Int. Microwave Symposium, Philadelphia, June 8-13, 2003.
doi: --- Either ISSN/ISBN or Series/Volume title must be supplied.