Overview of optimization methods in diagnostics of analog systems

• Autorzy: Bilski A. , Bilski P. , Wojciechowski J.

Warianty tytułu

PL

Zastosowania metod optymalizanych w diagnostyce systemów analogowych

• Języki publikacji: EN

Abstrakty

EN

The paper reviews the application of the optimization methods applied in diagnostics of analog systems. As multiple heuristic classification and regression algorithms are currently used, their parameters must be adjusted to maximize the diagnostic accuracy. First the diagnostic principles are introduced, focusing on the contemporary problems. Then, the most widely used optimization algorithms are classified and briefly described. Their applications to the main diagnostic problems arę discussed as well. The computational example illustrates the implementation of the Tabu Search algorithm to optimize the set of observed nodes in the complex analog circuit.

PL

Przeprowadzono przegląd zastosowań metod optymalizacyjnych w diagnostyce systemów analogowych. Optymalizacja jest stosowana w algorytmach klasyfikacji i regresji do strojenia wartości ich parametrów w celu uzyskania najjlepszej dokładności diagnostyki. Omówiono cele diagnostyki. W systematyzny sposób dokonano przeglądu problemów współczesnej diagnostyki. Przeprowadzono klasyfikację najczęściej stosowanych algorytmów i wskazano ich zastosowania. Ilustracyjny przykład pokazuje zastosowanie metody Tabu Search dla wyboru węzłów diagnostycznych, gwarantującego dostatecznie wysoką jakość diagnostyki.

Słowa kluczowe

EN

optimization; artificial intelligence; fault detection; analog systems

PL

optymalizacja; sztuczna inteligencja; wykrywanie uszkodzeń; systemy analogowe

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne
• Rocznik: 2015
• Tom: nr 6
• Strony: 611--617
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

Bilski A.

• Instytut Radioelektroniki, Wydział Elektroniki i Technik Informacyjnych Politechniki Warszawskiej

autor

Bilski P.

• Instytut Radioelektroniki, Wydział Elektroniki i Technik Informacyjnych Politechniki Warszawskiej

autor

Wojciechowski J.

• Instytut Radioelektroniki, Wydział Elektroniki i Technik Informacyjnych Politechniki Warszawskiej

Bibliografia

• [1] Milor L.S.: A Tutorial Introduction to Research on Analog and Mixed-Signal Circuit Testing. IEEE Trans, on Circuits and Systems-ll, vol. 45,no. 10,1998
• [2] Huertas I.L: Test and Design for Testability of Analog and Mixed-Signal Wegrated Circuits: Theoretical Basis and Pragmatical Approaches. Proc.ECCTD Conf., 1993
• [3] Bushnell L, Agrawal V. D.: Essentials of Electronic Testing for Digital, Memory and Mixed-Signal VLSI Circuits. Kluwer Academic Publishers, 2002, ISBN: 0-306-47040-3
• [4] Chakrabarti S., Cherubal S. and Chatterjee A.: Fault diagnosis for mixed-signal electronic systems, Proc. IEEE Aerospace Conference,1999
• [5] Samanta B.: Gear fault detection using artificial neural networks and Support vector machines wih genetic algorithms, Mechanical Systems and Signal Processing, 2004, no. 18
• [6] Seera M., Lim C.P., Ishak D., and Singh H.: Application of the fuzzy min-max neural network to faun detection and diagnosis of induction motore, Neural Comput&Applic, Springer Verlag, 2012
• [7] Muralidharan V. and Sugumaran V: A comparative study of Naive Bayes classifier fusion methods for chemical processes, Computers and Chemical Engineering, 2012, no. 34
• [8] Browning T. R.: Applying the design structure matrix to system decomposition and integration problems: a review and new directions, IEEE Trans. Eng. Management, Vol. 48, Issue 3, 2001
• [9] Tadeusiewicz M., Halgas S., and Korzybski M.: Multiple catastrophic fault diagnosis of analog circuits considering the component tolerances, Int. J. Circ. Theor. Appl. 2011
• [10] Samanta B., Nataraj C.: Use of particle swarm optimization for machinery fault detection, Engineering Applications of Artificial Intelligence, 2009,22(2)
• [11] Rutkowski J., Zieliński L.: Using evolutionary techniques for chosen optimization problems related to analog circuits design, Proc. 16thEuropean Conference on Circuits Theory and Design, Cracow, Poland, 2003, vol. 3
• [12] Abd-EI-Barr M.. M. Sait S., Sarif B. A. B., and Al-Saiari U.:A Modified Art Golony Algorithm for Evolutionary Design of Digital Circuits, Evolutionary Computation, CEC'03, vol.1, December 8-12, 2003
• [13] Benhala B., Ahaitouf A., Mechaqrane A., Benlahbib B., Abdi F., Abar-kan E. and Fakhfakh M.: Sizing of current comeyors by means of an ant colony optimization technique, The International Conference on Multimedia Computing and Systems, Morocco, April 7-9, 2011
• [14] Benhala B., Ahaitouf A., Fakhfakh M., Mechagrane A., Benlahbib B.: Optimal Analog Circuit Sizing via Art Colony Optimization Technique, IJCSNS International Journal of Computer Science and Network Security,VOL.11 No.6, June 2011
• [15] Starzyk J., D. Liu, Liu Z-H., Nelson D., and Rutkowski J.: Entropy-based optimum test nodes selection for analog fault dictionary techniques, IEEE Trans Instrum Meas, 2004, 53
• [16] Varghese X., Williams J. H. and Towill DR.: Computer aided feature selection for enhanced analogue system fault location, Pattems Recog, 1978,10(4)
• [17] Hochwald W., Bastian J. D.: A DC approach for analog fault dictionary determination, IEEE Trans Circ Syst CAS, 1979, 26
• [18] Lin PM., Elcherif Y S.: Analogue circuits fault dictionary - new approaches and implementation, Int J Circ Theory Appl, 1985,13(2)
• [19] Stenbakken G. N. and Souders T. M.: Test point selection and testability measure via QR factorization of linear models, IEEE Trans Instr. Meas., 1987, IM-36(6)
• [20] Spaandonk J., Kevenaar T.: lterative test point selection for analog circuits, Proc. 14th VLSI Test Symp, Princeton, NJ, USA, 1996
• [21] Golonek T. and Rutkowski J.: Genetic-algorithm-based method for optimal analog testpoints selection, IEEE Trans Circ Syst II Exp Brief, 2007
• [22]Gertler J.J., Costin M„ Fang X., Hira R., Kowalczuk Z., and Lou Q.: Model-based on board fault detection and diagnosis for automotive engines, Control Engineering Practice, 1993, Vol. 1, Issue 1
• [23] Geurts R, Irrthum A., and Wehenkel L.: Supervised learning with decision tree-based methods in computational and systems biology, Supplementary Materiał for Mdecular BioSystems, 2009
• [24] Samanta B.: Gear fault detection using artificial neural networks and support vector machines with genetic algorithms, Mechanical Systems and Signal Processing, 2004, no. 18
• [25] Mehala N., Dahiya R.: A Comparative Study of FFT, STFT and Wavelet Techniques for Induction Machine Fault Diagnostic Analysis, Proc. Of the 7th WSEAS Int. Conf. on Computational Intelligence, Man-Machine Systems and Cybemetics, 2008
• [26] Bilski R: Automated selection of kernel parameters in diagnostics of analog systems, Przegląd Elektrotechniczny, No. 5,2011
• [27] Yuana S. and Chu F: Fautt diagnostics based on particle swarm optimisation and support vector machines, Mechanical Systems and Signal Processing 21 (2007)
• [28] Roelofs H. H. B. and Heuvelman C.J.: Optimization of design tolerances of servomechanisms, Annals of the CIRR Vol. 41/1/1992
• [29] Golonek I, Rutkowski J.: Use of evolution strategies to analog testing with time domain stimuli, Proc. III ICSES, Świeradów Zdrój 2002
• [30] Kowalewski M.: Selection of excitation signals for high-impedance spectroscopy, Journal of Physics: Conference Series 459 (2013) 012060
• [31] Golonek T., Grzechca D., Rutkowski J.: Optimization of PWL analog testing excitation by means of genetic algorithm, Signals and Electronic Systems, 2008. ICSES '08. International Conference on, Kraków 14-17 Sept. 2008
• [32] Wang J., Wu G., Wan L, Sun Y, and Jiang D.: Recurrent Neural Network Applied to Fault Diagnosis of Underwater Robots, IEEE International Conference on Intelligent Computing and Intelligent Systems, 20-22 Nov. 2009, Shanghai