Zusammenfassung
In diesem Bericht wird ein erwartungstreues Filter mit endlicher Impulsantwort (Unbiased Finite Impulse Response/UFIR) zur Systemidentifikation mittels Parameterschätzung verwendet. Dieses entspricht einem Least-Squares-Verfahren auf bewegtem Horizont (Receding Horizon Least Squares/RHLS) ohne die Verwendung von Anfangsbedingungen und mit optimaler Horizontlänge für eine minimale Schätzfehlerkovarianz in Gegenwart von Parameter- und Messrauschen. Die Messwerte des Ausgangssignals werden von der Strecke über ein Netzwerk [basierend auf dem Transmission Control Protocol (TCP)] zum Parameterschätzer übertragen. Die dabei stochastisch auftretenden Paketverluste werden mit Hilfe multipler Imputationen kompensiert. Der Einfluss des Netzwerks auf die Schätzgüte wird untersucht und an einem numerischen Beispiel erläutert.
Abstract
An unbiased finite impulse response filter (UFIR filter) is used for parameter identification. The algorithm is equivalent to the receding horizon least squares method. But it does not require initial conditions and the horizon length is optimised to guarantee a minimal error covariance if there is parameter and measurement noise. The output measurements are sent to the UFIR estimator via a network based on the Transmission Control Protocol (TCP). The package dropouts are compensated by multiple imputations. The network influence on the parameter estimation is investigated and approved within numerical studies.
Über die Autoren
Dipl.-Ing. Steffen Siegl ist externer Doktorand am Institut für Steuer– und Regelungstechnik der Fakultät für Luft- und Raumfahrttechnik an der Universität der Bundeswehr München. Hauptarbeitsgebiete: Lineare Schätztheorie, Systemidentifikation, Networked Control Systems.
Prof. Dr.-Ing. Ferdinand Svaricek ist Leiter des Instituts für Steuer- und Regelungstechnik der Fakultät für Luft- und Raumfahrttechnik an der Universität der Bundeswehr München. Hauptarbeitsgebiete: Lineare und nichtlineare Regelung, aktive Schwingungskompensation, Anwendung moderner regelungs- und systemtheoretischer Methoden in der Mechatronik und der Kraftfahrzeugtechnik.
Literatur
1. P. Albertos, R. Sanchis and A. Sala. Output prediction under scarce data operation: control applications. Automatica, 35(10): 1671–1681, 1999.10.1016/S0005-1098(99)00078-3Search in Google Scholar
2. K. J. Åström and B. Wittenmark. Adaptive Control. Dover Publications, 2008. (2 rev. Dover ed.)Search in Google Scholar
3. C. Bohn and H. Unbehauen. Identifikation dynamischer Systeme. Springer Fachmedien Wiesbaden, 2016.10.1007/978-3-8348-2197-3Search in Google Scholar
4. L. Cao and H. M. Schwartz. Exponential convergence of the Kalman filter based parameter estimation algorithm. International Journal of Adaptive Control and Signal Processing, 17(10): 763–783, 2003.10.1002/acs.774Search in Google Scholar
5. J. Cioffi and T. Kailath. Windowed fast transversal filters adaptive algorithms with normalization. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(3): 607–625, 1985.10.1109/TASSP.1985.1164585Search in Google Scholar
6. O. Costa and S. Guerra. Stationary filter for linear minimum mean square error estimator of discrete-time Markovian jump systems. IEEE Transactions on Automatic Control, 47(8): 1351–1356, 2002.10.1109/TAC.2002.800745Search in Google Scholar
7. J. Deyst. Correction to “Conditions for asymptotic stability of the discrete minimum-variance linear estimator”. IEEE Transactions on Automatic Control, 18(5): 562–563, 1973.10.1109/TAC.1973.1100397Search in Google Scholar
8. J. Deyst and C. Price. Conditions for asymptotic stability of the discrete minimum-variance linear estimator. IEEE Transactions on Automatic Control, 13(6): 702–705, 1968.10.1109/TAC.1968.1099024Search in Google Scholar
9. F. Ding and T. Chen. Combined parameter and output estimation of dual-rate systems using an auxiliary model. Automatica, 40(10): 1739–1748, 2004.10.1016/j.automatica.2004.05.001Search in Google Scholar
10. F. Ding and T. Chen. Identification of dual-rate systems based on finite impulse response models. International Journal of Adaptive Control and Signal Processing, 18(7): 589–598, 2004.10.1002/acs.820Search in Google Scholar
11. F. Ding and J. Ding. Least-squares parameter estimation for systems with irregularly missing data. International Journal of Adaptive Control and Signal Processing, 24: 540–553, 2009.10.1002/acs.1141Search in Google Scholar
12. S. X. Ding. Model-Based Fault Diagnosis Techniques. Springer London, 2013.10.1007/978-1-4471-4799-2Search in Google Scholar
13. L. Guo. Estimating time-varying parameters by the Kalman filter based algorithm: stability and convergence. IEEE Transactions on Automatic Control, 35(2): 141–147, 1990.10.1109/9.45169Search in Google Scholar
14. K. Hashimoto, Y. Oishi and Y. Yamamoto. Control and Modeling of Complex Systems. Birkhäuser Boston, 2003.10.1007/978-1-4612-0023-9Search in Google Scholar
15. J. P. Hespanha, P. Naghshtabrizi and Y. Xu. A survey of recent results in networked control systems. Proceedings of the IEEE, 95(1): 138–162, 2007.10.1109/JPROC.2006.887288Search in Google Scholar
16. H. Heuser. Lehrbuch der Analysis. Vieweg + Teubner Verlag, 2000.10.1007/978-3-322-96812-8Search in Google Scholar
17. P. A. Ioannou and J. Sun. Robust Adaptive Control, Volume 1. Control Theory. PTR Prentice-Hall, 1996.Search in Google Scholar
18. A. H. Jazwinski. Stochastic Processes and Filtering Theory. Mathematics in Science and Engineering. Elsevier Science, 1970.Search in Google Scholar
19. R. Johnstone, C. Johnson, R. Bitmead and B. O. Anderson. Exponential convergence of recursive least squares with exponential forgetting factor. In 1982 21st IEEE Conference on Decision and Control. IEEE, 1982.10.1109/CDC.1982.268295Search in Google Scholar
20. P.-S. Kim. An alternative FIR filter for state estimation in discrete-time systems. Digital Signal Processing, 20(3): 935–943, 2010.10.1016/j.dsp.2009.10.033Search in Google Scholar
21. P.-S. Kim and M.-E. Lee. A new FIR filter for state estimation and its application. Journal of Computer Science and Technology, 22(5): 779–784, 2007.10.1007/s11390-007-9085-8Search in Google Scholar
22. S. Kluge, K. Reif and M. Brokate. Stochastic stability of the extended Kalman filter with intermittent observations. IEEE Transactions on Automatic Control, 55(2): 514–518, 2010.10.1109/TAC.2009.2037467Search in Google Scholar
23. F. Kozin. A survey of stability of stochastic systems. Automatica, 5(1): 95–112, 1969.10.1016/0005-1098(69)90060-0Search in Google Scholar
24. W. H. Kwon and S. H. Han. Receding Horizon Control: Model Predictive Control for State Models (Advanced Textbooks in Control and Signal Processing). Springer, 2005.Search in Google Scholar
25. W. H. Kwon, P. S. Kim and S. H. Han. A receding horizon unbiased FIR filter for discrete-time state space models. Automatica, 38(3): 545–551, 2002.10.1016/S0005-1098(01)00242-4Search in Google Scholar
26. W. H. Kwon, P. S. Kim and P. Park. A receding horizon Kalman FIR filter for discrete time-invariant systems. IEEE Transactions on Automatic Control, 44(9): 1787–1791, 1999.10.1109/9.788554Search in Google Scholar
27. M. Lin and S. Sra. Completely strong superadditivity of generalized matrix functions. Functional Analysis, arXiv:1410.1958v1 [math.FA], 2014.Search in Google Scholar
28. Y. Liu and F. Ding. Convergence properties of the least squares estimation algorithm for multivariable systems. Applied Mathematical Modelling, 37(1-2): 476–483, 2013.10.1016/j.apm.2012.03.007Search in Google Scholar
29. L. Ljung. System Identification: Theory for the User. Prentice Hall Information and System Sciences Series. Prentice Hall PTR, 1999.Search in Google Scholar
30. J. Lunze. Control Theory of Digitally Networked Dynamic Systems. Springer International Publishing, 2013.10.1007/978-3-319-01131-8Search in Google Scholar
31. F. L. Markley and J. R. Carpenter. Generalized linear covariance analysis. The Journal of the Astronautical Sciences, 57(1-2): 233–260, 2009.10.1007/BF03321503Search in Google Scholar
32. J. Nilsson, B. Bernhardsson and B. Wittenmark. Stochastic analysis and control of real-time systems with random time delays. Automatica, 34(1): 57–64, 1998.10.1016/S0005-1098(97)00170-2Search in Google Scholar
33. M. Petković, M. R. Rapaić, Z. D. Jeličić and A. Pisano. On-line adaptive clustering for process monitoring and fault detection. Expert Systems with Applications, 39(11): 10226–10235, 2012.10.1016/j.eswa.2012.02.150Search in Google Scholar
34. F. Ramirez-Echeverria, A. Sarr and Y. S. Shmaliy. Optimal memory for discrete-time FIR filters in state-space. IEEE Transactions on Signal Processing, 62(3): 557–561, 2014.10.1109/SSP.2012.6319701Search in Google Scholar
35. J. Reger und J. Jouffroy. Algebraische Ableitungsschätzung im Kontext der Rekonstruierbarkeit (Algebraic time-derivative estimation in the context of reconstructibility). at - Automatisierungstechnik, 56(6(2008)), 2008.10.1524/auto.2008.0711Search in Google Scholar
36. D. G. Robertson, J. H. Lee and J. B. Rawlings. A moving horizon-based approach for least-squares estimation. AIChE Journal, 42(8): 2209–2224, 1996.10.1002/aic.690420811Search in Google Scholar
37. D. B. Rubin. Multiple imputations in sample surveys-a phenomenological Bayesian approach to nonresponse. In Proceedings of the survey research methods section of the American Statistical Association, volume 1, pages 20–34. American Statistical Association, 1978.Search in Google Scholar
38. D. B. Rubin. Multiple Imputation for Nonresponse in Surveys (Wiley Series in Probability and Statistics). Wiley, 1987.10.1002/9780470316696Search in Google Scholar
39. D. K. Ryu, C. J. Lee, S. K. Park and M. T. Lim. Unbiased FIR filtering with incomplete measurement information. International Journal of Control, Automation and Systems, 18(2): 330–338, 2020.10.1007/s12555-018-0316-2Search in Google Scholar
40. L. Schenato. Optimal estimation in networked control systems subject to random delay and packet loss. In Proceedings of the 45th IEEE Conference on Decision and Control. IEEE, 2006.10.1109/CDC.2006.377700Search in Google Scholar
41. L. Schenato. Optimal estimation in networked control systems subject to random delay and packet drop. IEEE Transactions on Automatic Control, 53(5): 1311–1317, 2008.10.1109/TAC.2008.921012Search in Google Scholar
42. Y. Shi and H. Fang. Kalman filter-based identification for systems with randomly missing measurements in a network environment. International Journal of Control, 83(3): 538–551, 2009.10.1080/00207170903273987Search in Google Scholar
43. Y. S. Shmaliy. Unbiased FIR filtering of discrete-time polynomial state-space models. IEEE Transactions on Signal Processing, 57(4): 1241–1249, 2009.10.1109/TSP.2008.2010640Search in Google Scholar
44. Y. S. Shmaliy. Linear optimal FIR estimation of discrete time-invariant state-space models. IEEE Transactions on Signal Processing, 58(6): 3086–3096, 2010.10.1109/TSP.2010.2045422Search in Google Scholar
45. Y. S. Shmaliy. An iterative Kalman-like algorithm ignoring noise and initial conditions. IEEE Transactions on Signal Processing, 59(6): 2465–2473, 2011.10.1109/TSP.2011.2129516Search in Google Scholar
46. Y. S. Shmaliy and O. Ibarra-Manzano. Noise power gain for discrete-time FIR estimators. IEEE Signal Processing Letters, 18(4): 207–210, 2011.10.1109/LSP.2011.2108647Search in Google Scholar
47. Y. S. Shmaliy and D. Simon. Iterative unbiased FIR state estimation: a review of algorithms. EURASIP Journal on Advances in Signal Processing, 2013(1), 2013.10.1186/1687-6180-2013-113Search in Google Scholar
48. Y. S. Shmaliy, S. Zhao and C. K. Ahn. Unbiased finite impluse response filtering: an iterative alternative to Kalman filtering ignoring noise and initial conditions. IEEE Control Systems, 37(5): 70–89, 2017.10.1109/MCS.2017.2718830Search in Google Scholar
49. S. Siegl. Networked Control Systems: Ein Überblick. Technical report, Universität der Bundeswehr München Institut für Steuer– und Regelungstechnik, 2017.Search in Google Scholar
50. S. Siegl and F. Svaricek. UFIR-Parameteridentifikation in Echtzeit. at - Automatisierungstechnik, 68(3): 176–195, 2020.10.1515/auto-2019-0111Search in Google Scholar
51. D. Simon. Optimal State Estimation: Kalman, H∞, and Nonlinear Approaches. Wiley-Interscience, 2006.10.1002/0470045345Search in Google Scholar
52. B. Sinopoli, L. Schenato, M. Franceschetti, K. Poolla, M. I. Jordan and S. S. Sastry. Kalman filtering with intermittent observations. IEEE Transactions on Automatic Control, 49(9): 1453–1464, 2004.10.1109/CDC.2003.1272646Search in Google Scholar
53. C. Sonntag. Echtzeitadaptionsverfahren für Optimalregler mit Ausgangsrückführung für lineare Systeme. PhD thesis, Universität der Bundeswehr München/Fakultät für Elektrotechnik und Informationstechnik, 2017.Search in Google Scholar
54. T. Söderström and P. Stoica. System Identification (Prentice Hall International Series in Systems and Control Engineering). Prentice Hall, 1989.Search in Google Scholar
55. K. J. Uribe-Murcia, Y. S. Shmaliy, C. K. Ahn and S. Zhao. Unbiased FIR filtering for time-stamped discretely delayed and missing data. IEEE Transactions on Automatic Control, 65(5): 2155–2162, 2020.10.1109/TAC.2019.2937850Search in Google Scholar
56. S. van Buuren. Flexible Imputation of Missing Data, Second Edition. Taylor & Francis Ltd, 2018.10.1201/9780429492259Search in Google Scholar
57. M. Vazquez-Olguin, Y. S. Shmaliy, C. K. Ahn and O. G. Ibarra-Manzano. Blind robust estimation with missing data for smart sensors using UFIR filtering. IEEE Sensors Journal, 17(6): 1819–1827, 2017.10.1109/JSEN.2017.2654306Search in Google Scholar
58. M. Vazquez-Olguin, Y. S. Shmaliy, O. Ibarra-Manzano and L. J. Morales-Mendoza. Design of blind robust estimator for smart sensors. In Advances in Computational Intelligence, pages 354–365. Springer International Publishing, 2018.10.1007/978-3-030-02840-4_29Search in Google Scholar
59. E. D. Wilson, Q. Clairon, R. Henderson and C. Taylor. Dealing with observational data in control. Annual Reviews in Control, 46: 94–106, 2018.10.1016/j.arcontrol.2018.05.001Search in Google Scholar
60. Y. Xu. Communication scheduling methods for estimation over networks. PhD thesis, University of California, 2006.Search in Google Scholar
61. C. Yang, J. Zheng, X. Ren, W. Yang, H. Shi and L. Shi. Multi-sensor Kalman filtering with intermittent measurements. IEEE Transactions on Automatic Control, 63(3): 797–804, 2018.10.1109/TAC.2017.2734643Search in Google Scholar
62. P. C. Young. Recursive Estimation and Time-Series Analysis. Springer Berlin Heidelberg, 2011.10.1007/978-3-642-21981-8Search in Google Scholar
63. Q. Zhang. On stability of the Kalman filter for discrete time output error systems. Systems & Control Letters, 107: 84–91, 2017.10.1016/j.sysconle.2017.07.011Search in Google Scholar
64. X.-P. Zhang, A. S. Khwaja, J.-A. Luo, A. S. Housfater and A. Anpalagan. Multiple imputations particle filters: convergence and performance analyses for nonlinear state estimation with missing data. IEEE Journal of Selected Topics in Signal Processing, 9(8): 1536–1547, 2015.10.1109/JSTSP.2015.2465360Search in Google Scholar
65. S. Zhao, Y. S. Shmaliy, C. K. Ahn and F. Liu. Adaptive-horizon iterative UFIR filtering algorithm with applications. IEEE Transactions on Industrial Electronics, 65(8): 6393–6402, 2018.10.1109/TIE.2017.2784405Search in Google Scholar
66. S. Zhao, Y. S. Shmaliy and F. Liu. On the iterative computation of error matrix in unbiased FIR filtering. IEEE Signal Processing Letters, 24(5): 555–558, 2017.10.1109/LSP.2017.2682641Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
