Automatic parametric fault detection in complex analog systems based on a method of minimum node selection

• Autorzy: Bilski A. , Wojciechowski J.

Identyfikatory

DOI

10.1515/amcs-2016-0045

• Języki publikacji: EN

Abstrakty

EN

The aim of this paper is to introduce a strategy to find a minimal set of test nodes for diagnostics of complex analog systems with single parametric faults using the support vector machine (SVM) classifier as a fault locator. The results of diagnostics of a video amplifier and a low-pass filter using tabu search along with genetic algorithms (GAs) as node selectors in conjunction with the SVM fault classifier are presented. General principles of the diagnostic procedure are first introduced, and then the proposed approach is discussed in detail. Diagnostic results confirm the usefulness of the method and its computational requirements. Conclusions on its wider applicability are provided as well.

Słowa kluczowe

EN

complex analog system; support vector machine (SVM); tabu search; genetic algorithm; parametric fault detection

PL

system analogowy; maszyna wektorów wspierających; metoda tabu search; algorytm genetyczny; detekcja uszkodzeń

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2016
• Tom: Vol. 26, no. 3
• Strony: 655--668
• Opis fizyczny: Bibliogr. 46 poz., rys., tab., wykr.

Twórcy

autor

Bilski A.

• Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences—SGGW, ul. Nowoursynowska 159, 02-776 Warsaw, Poland

autor

Wojciechowski J.

• Institute of Radioelectronics, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, Poland

Bibliografia

• [1] Aminian, F. and Modular, A.(2007). Fault-diagnostic system for analog electronic circuit using neural networks with wavelet transform as a preprocessor, IEEE Transactions on Instrumentation and Measurement 56(5): 1546–1554.
• [2] Arabas, J. (2004). Lectures in Evolutionary Algorithms, WNT, Warsaw, (in Polish).
• [3] Bilski, A. (2013). Diagnostic of complex analog systems with parametric faults using support vector machines, in T. Kwater and B. Twaróg (Eds.), Computing in Science and Technology 2012/13, University of Rzeszow, Rzeszów, pp. 7–24.
• [4] Bilski, P. (2007). Automated diagnostic system using graph clustering algorithm and fuzzy logic method, 18th European Conference on Circuit Theory and Design 2007, Seville, Spain, pp. 779–782.
• [5] Bilski, P. (2011). Automated selection of kernel parameters in diagnostics of analog systems, Przegląd Elektrotechniczny 87(5): 9–13.
• [6] Bilski, P. and Wojciechowski, J. (2007). Automated diagnostics of analog systems using fuzzy logic approach, IEEE Transactions on Instrumentation and Measurement 56(6): 2175–2185.
• [7] Bilski, P. and Wojciechowski, J. (2012). Current research trends in diagnostics of analog systems, 2012 International Conference on IEEE Signals and Electronic Systems (ICSES), Wrocław, Poland, pp. 1–11.
• [8] Bushell, L. and Vishwani, D.A. (2002). Essentials of Electronic Testing for Digital, Memory and Mixed-Signal VLSI Circuits, Springer US, New York, NY.
• [9] Czaja, Z. and Zielonko, R. (2004). On fault diagnosis of analogue electronic circuits based on transformations in multidimensional spaces, Measurement 35(3): 293–301.
• [10] Chakrabarti, S., Cherubal, S. and Chatterjee, A. (1999). Fault diagnosis for mixed-signal electronic systems, IEEE Aerospace Conference, Snowmass at Aspen, CO, USA, pp. 169–179.
• [11] Chatterjee, A., Kim, B. and Nagi, N. (1996 ). DC built-in self-test for linear analog circuits, IEEE Design and Test of Computers 13(2): 26–33.
• [12] Fang, L., Plamen, K.N. and Sule, O. (2006 ). Parametric fault diagnosis for analog circuits using a Bayesian framework, Proceedings of the 24th IEEE VLSI Test Symposium VTS’06, Berkeley, CA, USA, pp. 272–277.
• [13] Gendreau, M. (2003). An introduction to tabu search, in F. Glover and G.A. Kochenberger (Eds.), Handbook of Metaheuristics, Springer, US, New York, NY, pp. 37–54.
• [14] Grzechca, D., Golonek, T. and Rutkowski, J. (2006). Analog fault AC dictionary creation—the fuzzy set approach, IEEE International Symposium on Circuits and Systems, Kos, Greece, pp. 5744–5747.
• [15] Grzechca, D., Golonek, T. and Rutkowski, J. (2007). Simulated annealing with fuzzy fitness function for test frequencies selection, Proceedings of the IEEE Conference on Fuzzy Systems, London, UK, pp. 1–6.
• [16] Grasso, F., Luchetta, A., Manetti, S. and Piccirilla, M.C. (2007). Method for the automatic selection of test frequencies in analog fault diagnosis, IEEE Transactions on Instrumentation and Measurement 56(6): 2322–2329.
• [17] Golonek, T., Grzechca, D. and Rutkowski, J. (2008). Optimization of PWL analog testing excitation by means of genetic algorithm, Proceedings of the International Conference on Signals and Electronic Systems, Kraków, Poland, pp. 541–548.
• [18] Golonek, T. and Rutkowski, J. (2007). Genetic-algorithm-based method for optimal analog test points selection, IEEE Transactions on Circuits and Systems II 54(2): 117–121.
• [19] Guo, Y.-M., Wang, X.-T., Liu, Ch., Zheng, Y.-F. and Cai, X.-B. (2014). Electronic system fault diagnosis with optimized multi-kernel SVM by improved CPSO, Maintenance and Reliability 16(1): 85–91.
• [20] Hochwald, W. and Bastian, J.D. (1979). A DC dictionary approach for analog fault dictionary determination, IEEE Transactions on Circuits and Systems 26(7): 523–529.
• [21] Huertas, I.L (1993). Test and design for testability of analog and mixed-signal integrated circuits: Theoretical basis and pragmatical approaches, Proceedings of the European Conference on Circuit Theory and Design, Davos, Switzerland, pp. 1389–1407.
• [22] Huang, K., Stratigopoulos, H.-G. and Mir, S. (2010). Fault diagnosis of analog circuits based on machine learning, 2010 Design, Automation and Test in Europe Conference and Exhibition (DATE 2010), Dresden, Germany, pp. 1761–1766.
• [23] Jantos, P., Grzechca, D. and Rutkowski, J. (2009). A global parametric faults diagnosis with the use of artificial neural networks, European Conference on Circuit Theory and Design, Antalya, Turkey, pp. 651–655.
• [24] Jantos, P., Grzechca, D. and Zielonko, R. (2009). Global parametric faults identification in analog electronic circuits, Metrology and Measurement Systems 16(3): 391–402.
• [25] Korbicz, J., Obuchowicz, A. and Uciński, D. (1994). Artificial Neural Networks. Fundamentals and Applications, PLJ, Warsaw, (in Polish).
• [26] Kuczyński, A. and Ossowski, M. (2009). Analog circuits diagnosis using discrete wavelet transform of supply current, Metrology and Measurement Systems 16(1): 77–85.
• [27] Milor, L.S. (1998). A tutorial introduction to research on analog and mixed-signal circuit testing, IEEE Transactions on Circuits and Systems II 41(10): 1389–1407.
• [28] Nguyen, W.H. and Golinval, J.-C. (2010). Fault detection based on kernel principal component analysis, Engineering Structures 32(11): pp. 3683–3691.
• [29] Osowski, S. (2006). Artificial Neural Networks for Information Processing, Warsaw University of Technology Press, Warsaw, (in Polish).
• [30] Ohletz, M. (1991). Hybrid built-in self-test for mixed analog/digital integrated circuits, European Test Conference, Munich, Germany, pp. 307–316.
• [31] Pan, C. and Cheng, K.-T. (1995). Pseudorandom testing and signature analysis for mixed-signal systems, IEEE International Conference on Computer-Aided Design, San Jose, CA, USA, pp. 102–107.
• [32] Prasad, V.C. and Babu, N.S.C. (2000). Selection of test nodes for analog fault diagnosis in dictionary approach, IEEE Transactions on Instrumentation and Measurement 49(6): 1289–1297.
• [33] Rutkowski, J. and Grzechca, D. (2009). Fault diagnosis in analog electronic circuits—the SVM approach, Metrology and Measurement Systems 16(4): 583–598.
• [34] Salama, A.E., Starzyk, J.A. and Bandler, J.W. (1984). A unified decomposition approach for fault location in large analog circuits, IEEE Transactions on Circuits and Systems 31(7): 609–622.
• [35] Sałat, R. and Osowski, S. (2011). Support vector machine for soft fault location in electrical circuits, Journal of Intelligent and Fuzzy Systems 22(1): 21–31.
• [36] Sen, N. and Saeks, R. (1979 ). Fault diagnosis for linear systems via multifrequency measurements, IEEE Transactions on Circuits and Systems 26(7): 457–465.
• [37] Starzyk, J.A. and Dai, H. (1992 ). A decomposition approach for testing large analog networks, Journal of Electronic Testing: Theory and Applications 3(3): 181–195.
• [38] Starzyk, J.A., Liu, D., Liu, Z.-H., Nelson, D.E. and Rutkowski, J. (2004). Entropy-based optimum test points selection for analog fault dictionary techniques, IEEE Transactions on Instrumentation and Measurement 53(2): 754–761.
• [39] Sun, J., Wang, Ch., Sun, J. and Wang, L. (2013). Analog circuit soft fault diagnosis based on PCA and PSO-SVM, Journal of Networks 8(12): 2791–2796.
• [40] Spina, R. and Upadhyaya, S. (1997). Linear circuit fault diagnosis using neuromorphic analyzers, IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing 44(3): 188–196.
• [41] Tadeusiewicz, M., Hałgas, S. and Korzybski, M. (2011). Multiple catastrophic fault diagnosis of analog circuits considering the component tolerances, International Journal of Circuit Theory Application 44(3): 188–196.
• [42] Tadeusiewicz, M. and Korzybski, M. (2000). A method for fault diagnosis in linear electronic circuits, International Journal of Circuit Theory and Applications 28(3): 245–262.
• [43] Tadeusiewicz, M. and Hałgas, S. (2006). An algorithm for multiple fault diagnosis in analogue circuits, International Journal of Circuit Theory and Applications 34(6): 607–615.
• [44] Widodo, A. and Bo-Suk, T. (2007). Support vector machine in machine condition monitoring and fault diagnosis, Mechanical Systems and Signal Processing 21(6): 2560–2574.
• [45] Wang, P. and Yang, S. (2005). A new diagnosis approach for handling tolerance in analog and mixed-signal circuits by using fuzzy math, IEEE Transactions on Circuits and Systems I: Regular Papers 52(10): 2118–2127.
• [46] Vapnik, V. and Cortes, C. (1995). Support-vector networks, Machine Learning 20(3): 273–297.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.