A MLMVN with arbitrary complex-valued inputs and a hybrid testability approach for the extraction of lumped models using FRA

• Autorzy: Aizenberg Igor , Luchetta Antonio , Manetti Stefano , Piccirilli Maria Cristina

Identyfikatory

DOI

10.2478/jaiscr-2018-0021

• Języki publikacji: EN

Abstrakty

EN

A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.

Słowa kluczowe

EN

analog circuits; complex-valued neural networks; lumped model; testability

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2019
• Tom: Vol. 9, No. 1
• Strony: 5--19
• Opis fizyczny: Bibliogr. 41 poz., rys.

Twórcy

autor

Aizenberg Igor

• Manhattan College, Riverdale, New York, USA

autor

Luchetta Antonio

• Dept. of Information Engineering, University of Florence, Firenze, Italy

autor

Manetti Stefano

• Dept. of Information Engineering, University of Florence, Firenze, Italy

autor

Piccirilli Maria Cristina

• Dept. of Information Engineering, University of Florence, Firenze, Italy

Bibliografia

• [1] A. Hirose, Complex-Valued Neural Networks, 2nd Edn., Springer, Berlin, Heidelberg, 2012.
• [2] Y.Nakano, A.Hirose, Improvement of plastic landmine visualization performance by use of ringCSOM and frequency-domain local correlation, IEICE Transactions on Electronics, vol. E92-C, no. 1, pp. 102-108, Jan. 2009.
• [3] S. L. Goh, M. Chen, D. H. Popovic, K. Aihara, D. Obradovic and D. P. Mandic, Complex Valued Forecasting of Wind Profile, Renewable Energy, vol. 31, pp. 1733-1750, Sep. 2006.
• [4] A. Handayani, A.B.Suksmono, T.L.R.Mengko, and A.Hirose, Blood Vessel Segmentation in ComplexValued Magnetic Resonance Images with Snake Active Contour Model, International Journal of EHealth and Medical Communications, vol. 1, no. 1, pp. 41-52, Jan. 2010.
• [5] G. Avitabile, B. Chellini, G. Fedi, A. Luchetta and S. Manetti, A neural architecture for the parameter extraction of high frequency devices, in Proc. of IEEE Int. Symposium on Circuits and Systems (ISCAS), Sidney, Australia, 2001, pp. 577-580.
• [6] V. Rashtchi, E. Rahimpour, and E. M. Rezapour, Using a genetic algorithm for parameter identification of transformer R-L-C-M model, Electrical Engineering, 88, no.5, 417-422, June 2006.
• [7] A. Shinterimov, W. J. Tang, W. H. Tang, and Q. H. Wu, Improved modelling of power transformer winding using bacterial swarming algorithm and frequency response analysis, Electric Power Systems Research, 80, no. 9, 1111-1120, Sep. 2010.
• [8] W. H. Tang, S. He, Q. H. Wu and Z. J. Richardson, Winding deformation identification using a particle swarm optimiser with passive congregation of power transformes. Int. J. of Innovations in Energy Systems and Power, 1(11), 46-52, 2006.
• [9] I. Aizenberg, A. Luchetta, S. Manetti and M.C. Piccirilli, ” System Identification using FRA and a modified MLMVN with Arbitrary Complex-Valued Inputs”, Proc. of the IEEE International Joint Conference on Neural Networks (IJCNN’16), Vancouver, July 2016, pp. 4404-4411.
• [10] N.N. Aizenberg and I.N. Aizenberg, ”CNN Based on Multi-Valued Neuron as a Model of Associative Memory for Gray-Scale Images”, Proceedings of the Second IEEE International Workshop on Cellular Neural Networks and their Applications, Munich, October 14-16, 1992, pp.36-41.
• [11] I. Aizenberg, and C. Moraga, Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm, Soft Computing, 11, no. 2, 169-183, Jan.2007.
• [12] N. Sen and R. Saeks, Fault Diagnosis for Linear System via Multifrequency Measurement”, IEEE trans. Circuits and Systems, vol. CAS-26, pp.457 -465, 1979.
• [13] N. N. Aizenberg, L. Ivaskiv, D. A. Pospelov, and G.F. Hudiakov, Multivalued Threshold Functions. II. Synthesis of Multivalued Threshold Elements, Cybernetics and Systems Analysis, vol. 9, no. 1, pp. 61-77, Jan 1973.
• [14] I. Aizenberg,, C. Moraga, and D. Paliy, A Feedforward Neural Network based on Multi-Valued Neurons, In Computational Intelligence, Theory and Applications. Advances in Soft Computing, XIV, (B. Reusch - Ed.), Springer, Berlin, Heidelberg, New York, 2005, pp. 599-612.
• [15] I. Aizenberg, I., Complex-Valued Neural Networks with Multi-Valued Neurons. Berlin: Springer-Verlag Publishers, 2011.
• [16] I. Aizenberg, D. Paliy, J. Zurada, and J. Astola, Blur identification by multilayer neural network based on multivalued neurons, IEEE Transactions on Neural Networks, vol. 19, no. 5, 883-898, May 2008.
• [17] I. Aizenberg, A. Luchetta and S. Manetti, S, A modified learning algorithm for the multilayer neural network with multi-valued neurons based on the complex QR decomposition, Soft Computing, vol. 16, no. 4, 563-575, Apr. 2012.
• [18] N.V.Manyakov, I. Aizenberg, N. Chumerin, and M. Van Hulle, Phase-Coded Brain-Computer Interface Based on MLMVN, book chapter in ComplexValued Neural Networks: Advances and Applications (A. Hirose – Ed.), Wiley, 2012, pp. 185-208.
• [19] I. Aizenberg, Hebbian and Error-Correction Learning for Complex-Valued Neurons, Soft Computing, vol. 17, no. 2, pp. 265-273, Feb. 2013.
• [20] I. Aizenberg, Adjustments to the proofs of the convergence theorems, available online at http://www.eagle.tamut.edu/faculty/igor/CVNNMVN book Convergence Proofs Adjustments.htm (2013).
• [21] G. Fedi, A. Luchetta, S. Manetti, and M. C. Piccirilli, A new symbolic method for analog circuit testability evaluation, IEEE Transactions on Instrumentation and Measurement, vol. 47, no. 10, 554-565, Apr. 1998.
• [22] A. Liberatore, S. Manetti, and M. C. Piccirilli, A new efficient method for analog circuit testability measurement. Proc. of IMTC’94, Hamamatsu, Japan, pp. 193-196, 1994.
• [23] G. Fedi, S. Manetti, M. C. Piccirilli, and J. Starzyk, Determination of an optimum set of testable components in the fault diagnosis of analog linear circuits, IEEE Transactions on Circuits and Systems - Part I, 46, 779-787, Jul. 1999.
• [24] S. Manetti, and M. C. Piccirilli, A singular-value decomposition approach for ambiguity group determination in analog circuits, IEEE Transactions on Circuits and Systems – Part I, vol. 50, no. 4, 477-487, Apr. 2003.
• [25] G. Fontana, A. Luchetta, S. Manetti and M. C. Piccirilli An unconditionally sound algorithm for testability analysis in linear time-invariant electrical networks, Int. J. On Circuit Theory and Applications, vol. 44 no. 6, pp. 1308-1340, 2016.
• [26] G. Fontana, A. Luchetta, S. Manetti, M. C. Piccirilli, A Fast Algorithm for Testability Analysis of Large Linear Time-Invariant Networks, IEEE Trans. on Circuits and Systems – Part I, DOI: 10.1109/TCSI.2016.2645079, 2017.
• [27] R. Berkowitz, Conditions for network-elementvalue solvability, IRE Trans. Circ. Theory, vol. 9, pp. 24-29, 1962.
• [28] W. J. Deika, A review of measures of testability for analog systems, Proc. Int. Autom. Test Conf. (AUTOTESTCON), 1977, pp. 279-284.
• [29] R. W. Priester, J. B. Clary, New measures of testability and test complexity for linear analog failure, IEEE Trans. Circuits Syst., vol. 30, pp. 884-888, 1981.
• [30] C. Lin, Z. F. Huang, R. Liu, Topological conditions for single-branch-fault, IEEE Trans. Autom. Control, vol. 28, pp. 689-694, 1983.
• [31] G. N. Stenbakken, T. M. Souders, Test-point selection and testability measures via QR factorization of linear models, IEEE Trans. Instrum. Meas., vol. 36, pp. 406-410, 1987.
• [32] G. N. Stenbakken, T. M. Souders and G. W. Stewart, Ambiguity groups and testability, IEEE Trans. Instrum. and Meas., vol. 38, pp.941-947, 1989.
• [33] W. H. Huang and C. L. Wey, Diagnosability analysis of analogue circuits, Int. J. Circ. Theor. Appl., vol. 26, pp. 439–451, 1998.
• [34] J. A. Starzyk and M. A. El-Gamal, Diagnosability of analog circuits-a graph theoretical approach, Proc. IEEE Int. Symp. Circuits and Systems, 1988, pp. 945-948.
• [35] B. Cannas, A. Fanni and A. Montisci, Testability evaluation for analog linear circuits via transfer function analysis Proc. IEEE Int. Symp. Circuits and Systems, 2005, pp. 992-995.
• [36] F. Grasso, A. Luchetta, S. Manetti, M. C. Piccirilli and A. Reatti, SapWin 4.0–a new simulation program for electrical engineering education using symbolic analysis, Computer Applications in Engineering Education, vol. 24 no. 1, pp. 44-57, 2016.
• [37] W. S. Bennett, Properly Applied Antenna Factors, IEEE Trans. on Electromagnetic Compatibility, EMC-28, 1, pp. 2-6, Feb. 1986.
• [38] G. Fedi, S. Manetti, G. Pelosi and S. Selleri, FEMtrained artificial neural networks for the analysis and design of cylindrical posts in rectangular waveguide, Electromagnetics, 22, 323–330, 2002.
• [39] G. Pelosi, R. Coccioli, and S. Selleri, Quick finite elements method for electromagnetic waves, (pp. 89–113). London: Artech House, 1998.
• [40] Shinterimov, W.H. Tang, and Q.H. Wu, Transformer Core Parameter Identification Using Frequency Response Analysis, IEEE Trans. on Magnetics, vol. 46, pp. 141-149, January 2010.
• [41] D. Roger, E. Napieralska-Juszczak, and A. Henneton, High frequency extension of non-linear models of laminated cores, Int. J. Comput. Math. Electr. Electron. Eng., vol. 25, pp. 140-156, 2009.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).