Modelowanie i sterowanie ukladów nieliniowych metodami neuropodobnymi

• Autorzy: Dzieliński A.
• Języki publikacji: PL

Abstrakty

PL

Rozprawa niniejsza powstała jako wynik prac autora w dziedzinie wykorzystania sieci neuronowych do modelowania i sterowania nieliniowych układów dynamicznych. Celem prac prowadzonych w latach 1992-2001 było zbadanie możliwości wykorzystania sieci neuronowych do modelowania i sterowania adaptacyjnego układami nieliniowymi. Badania były prowadzone w ramach projektów naukowych, realizowanych w Instytucie Sterowania i Elektroniki Przemysłowej Politechniki Warszawskiej oraz w Centre for Systems and Control, University of Glasgow. W pracy przedstawiono gruntowną analizę neuronowego sterowania adaptacyjnego. Podano struktury i algorytmy sieci neuronowych do modelowania, identyfikacji i sterowania nieliniowych układów dynamicznych. Podano również ocenę prezentowanych metod z perspektywy teorii sterowania nieliniowego. Rezultaty prezentowane w pracy mogą służyć za solidną podstawę do opracowania inżynierskiej metodologii projektowania neuronowych układów sterowania adaptacyjnego.

EN

This thesis has emerged as a result of the research, in the area of neural networks application to modelling and control of nonlinear dynamical systems, its author has been involved in. The goal of the research carried on in the years 1992-2001 was to examine the possibilities of applying the neural networks to modelling and adaptive control of nonlinear systems. These were the subjects of several scientific projects successfully completed in the Institute of Control and Industrial Electronics, Warsaw University of Technology and in the Centre for Systems and Control, University of Glasgow. In this book a detailed analysis of neural adaptive systems is presented. Several structures and learning algorithms for modelling, identification and control of nonlinear dynamical systems are given. Also the evaluation of the methods presented is given from the point of view of nonlinear control theory. The results presented in the thesis may serve as a firm foundation for elaboration of an engineering methodology for designing neural, nonlinear, adaptive control systems.

Słowa kluczowe

PL

układy dynamiczne; sieci neuronowe; aproksymacja transformaty Fouriera; układy NARX; sterowanie neuropodobne

• Wydawca: Oficyna Wydawnicza Politechniki Warszawskiej
• Czasopismo: Prace Naukowe Politechniki Warszawskiej. Elektryka
• Rocznik: 2002
• Tom: z. 119
• Strony: 3--184
• Opis fizyczny: Bibliogr. 224 poz., tab., rys., wykr.

Twórcy

autor

Dzieliński A.

• Wydział Elektryczny, Politechnika Warszawska

• Wydział Elektryczny Politechniki Warszawskiej

Bibliografia

• [1] K. J. Åström, B. Wittenmark. Adaptive Control. Addison-Wesley, Reading, Massachusetts, wydanie drugie, 1995.
• [2] K. J. Åström, B. Wittenmark. Computer Controlled Systems. Theory and Design. Prentice-Hall, Upper Saddle River, NJ, wydanie trzecie, 1997.
• [3] R. P. Agarwal Properties of solutions of higher order nonlinear difference equations. I. Analele Ştiinţifice ale Universităţii “Al. I. Cuza” din Iaşi (Serie Nouă). Matematică, XXXI(2):165-172, 1985.
• [4] R. P. Agarwal. Difference Equations and lnequalities. Theory, Methods, and Applications. Marcel-Dekker, Inc., New York. 1992.
• [5] E. Alpaydin. GAL: Networks that grow when they learn and shrink when they forget. Raport instytutowy 91-032, Int. Comp. Sci. Inst., Berkeley, 1991.
• [6] J. Alvarez, J. Alvarez. A tracking and regulation control scheme for discrete time nonlinear systems. Proceedings of the 28th IEEE Conference on Decision and Control, s. 535-536, Tampa, Florida, 1989.
• [7] J. Alvarez, J. Alvarez. Tracking and regulation reference model control of nonlinear systems. Preprints of the IFAC Symposium on Nonlinear Control Systems Design, NOLCOS, s. 466-471, Capri, Italy, 1989.
• [8] J. Alvarez. Tracking and regulation reference model control of nonlinear systems. Preprints of the 3rd IFAC Symposium on Nonlinear Control Systems Design, NOLCOS, s. 765-770, Tahoe City, California, 1995. IFAC.
• [9] V. I. Arnol'd. Some questions of approximation and representation of functions. Proceedings of the International Congress of Mathematicians, s. 339-348, 1958. (English translation: American Mathematical Society Transactions, vol. 53).
• [10] K. J. Åström, P. Hagander, J. Sternby. Zeros of sampled systems. Automatica, 20(1):31-38, 1984.
• [11] G. Becker, A. Packard. Robust performance of linear parametrically varying systems using parametrically-dependent linear feedback. Systems and Control Letters, 23:205-215, 1994.
• [12] J. L. Bently. Multidimensional binary search trees used for associative searching. Communications of the ACM, 18(9):509-517, 1975.
• [13] P. Biler, A. Witkowski Problems in Mathematical Analysis. Marcel-Dekker, Inc., New York and Basel, 1990.
• [14] R. P. Boas. Entire Functions. Academic Press, New York, 1954.
• [15] L. Breiman, J. H. Friedman, R. A. Olshen, C. J. Stone. Classification and Regression Trees. Wadsworths & Brooks, Monterey, Ca., 1984.
• [16] J. L. Brown. Sampling reconstruction of n-dimensional bandlimited images after multilinear filtering. IEEE Trans. on Circuits & Systems, CAS-36:1035-1038, 1989.
• [17] J. C. Burkill, H. Burkill. A Second Course in Mathematical Analysis. Cambridge University Press, Cambridge, England, 1970.
• [18] J. A. Cadzow. Foundations of Digital Signal Processing and Data Analysis. Macmillan Publishing Company, New York, 1987.
• [19] M. Carlin. Radial Basis Function networks and nonlinear data modeling. Neuro-Nimes 92, s. 623-633, 1992.
• [20] S. Chen, S. A. Billings, C. F. Cowan, P. M. Grant. Practical identification of NARMAX models using radial basis functions. International Journal of Control, 52:1327-1350, 1990.
• [21] S. Chen, S. A. Billings, P. M. Grant. Non-linear system identification using neural networks. International Journal of Control, 51:1191-1214, 1990.
• [22] S. Chen, S. A. Billings. Representation of nonlinear systems: the NARMAX model. International Journal of Control, 49(3):1013-1032, 1989.
• [23] S. Chen, C. F. N. Cowan, P. M. Grant. Orthogonal least squares learning algorithm for Radial Basis Function networks. IEEE Transactions on Neural Networks, 2(2):302-309, 1991.
• [24] T. Chen, H. Chen. Approximation of continuous functionals by neural networks with application to dynamic systems. IEEE Transactions on Neural Networks, 4:910-918, 1993.
• [25] K. F. Cheung. A multidimensional extension of Papoulis' Generalised Sampling Expansion with the application in minimum density sampling. Robert J. Marks II, red., Advanced Topics in Shannon Sampling and lnterpolation Theory. Springer Verlag, New York, 1993.
• [26] J. B. Conway. Functions of One Comp/ex Variable. Springer-Verlag, New York, wydanie drugie, 1978.
• [27] C. Corduneanu. Application of differential inequalities to stability theory. Analele Ştiinţifice ale Universităţii .,Al. I. Cuza" din Iaşi (Serie Nouă). Secţiunea I (Matematică, Fizică, Chimie), VI(I):47-58, 1960.
• [28] C. Corduneanu. Addendum to the paper "Application of differential inequalities to stability theory". Analele Ştiinţifice ale Universităţii ., “Al. I. Cuza" din Iaşi (Serie Nouă). Secţiunea I (Matematică, Fizică, Chimie), V II(2):247-252, 1961.
• [29] C. Corduneanu. On partial stability. Revue Roumaine de Mathématiques Pures et Appliquées, lX(3):229-236, 1964.
• [30] G. Cybenko. Approximation by superposition of a sigmoidal function. Mathematics of Control, Signals and Systems, 2:303-314, 1989.
• [31] C. A. Desoer, M. Vidyasagar. Feedback Systems: Input-Output Properties. Academic Press, New York, 1975.
• [32] H. Diaz, A. A. Desrochers. Modeling of nonlinear discrete-time systems from input-output data. Automatica, 24(5):629-641, 1988.
• [33] W. Duch, J. Korbicz, L. Rutkowski, R. Tadeusiewicz, red .. Biocybernetyka i inżynieria biomedyczna 2000 , vol. 6. Sieci neuronowe. Akademicka Oficyna Wydawnicza EXIT, Warszawa, 2000.
• [34] J. Dugundji. Topology. Allyn and Bacon, Boston, 1966.
• [35] R. A. Dwyer. Higher-dimensional Voronoi diagrams in linear expected time. Discrete & Computational Geometry , 6(4):343-367, 1991.
• [36] A. Dzieliński, J. Szostakowski. Simulation of nonlinear dynamic systems. Proceedings of the International Symposium on Nonlinear Theory and its Applications, NOLTA'98, s. 243-246, Crans-Montana, Switzerland, September 14-17 1998.
• [37] A. Dzieliński, R. Żbikowski, T. Kaczorek. Persistency of excitiation of identification with N-D sampling neural networks. R. Barlik, K. Duszczyk, red., Proceedings of the IEEE International Symposium o n Industrial Electronics, June 17-20, 1996, Warsaw, Poland, vol. l , s. 121-126, 1996.
• [38] A. Dzieliński, R. Żbikowski. Multidimensional sampling aspects of neurocontrol with feedforward networks. D. Lowe, red., Proceedings of 4th International Conference on Artificial Neural Networks, ICANN '95, June 26-28, 1995, Cambridge, England, s. 240-244, London, 1995. IEE.
• [39] A. Dzieliński, R. Żbikowski. N-dimensional sampling as a tool for nonlinear neurocontrol. S. Bańka, S. Domek, Z. Emirsajłow, red., Proceedings of the Second International Symposium on Methods and Models in Automation and Robotics, MMAR '95, August 30 - September 2, 1995, Międzyzdroje, Poland, s. 69-74, Szczecin, Poland, 1995. Szczecin University of Technology Press.
• [40] A. Dzieliński, R. Żbikowski. An algorithm for discrete-time dynamics modelling via N-D function reconstruction. Proceedings of 9'h Conference of the Europeon Consortium for Mathemarics in Industry , ECM/'96, June 25-29, 1996, Copenhagen, Denmark, s. 668-670, 1996.
• [41] A. Dzieliński, R. Żbikowski. Irregular sampling approach to neurocontrol with feedforward neural networks. S. W. Ellacott, J. C. Mason, I. J. Anderson, red., Mathematics of Neural Networks, Operations Research/Computer Science Interfaces Series, s. 166-170. Kluwer Acadernic Publishers, Dordrecht, The Netherlands, 1996.
• [42] A. Dzieliński, R. Żbikowski. New algorithm for neural networks modelling of nonlinear control systems. Proceedings of World Congress on Neural Networks, W CNN'96, September 15-18, 1996, San Diego, California, s. 465-468, 1996.
• [43] A. Dzieliński, R. Żbikowski. A new approach to neurocontrol based on Fourier analysis and nonuniform multi-dimensional sampling. Applied Mathematic s and Computer Science, 6(3):101-121, 1996.
• [44] A. Dzieliński, R. Żbikowski. New method of nonlinear systems identification. Proceedings of IMACS Multiconference on Computational Engineering in Systems Applications, CESA'96, July 10-13, 1996 , Lilie, France, 1996.
• [45] A. Dzieliński, R. Żbikowski. N-D nonuniform sampling approach to neurocontrol: A guided tour. Proceedings of UKACC International Conference, CONT ROL'96, September 2-5 , 1996, Exeter, England, s. 987-992, 1996.
• [46] A. Dzieliński. Optimal Filtering and Control of Two-dimensional Linear Discrete-Time Systems. Praca doktorska, Faculty of Electrical Engineering, Warsaw University of Technology, Warsaw, Poland, February 1992.
• [47] A. Dzieliński. Software for identification of hybrid nonlinear systems. Proceedings of the IMACS Multiconference on Computational Engineering in Systems Applications, CESA'98, Hammamet, Tunisia, April - 4, 1998.
• [48] A. Dzieliński. Software for identitication of nonlinear systems. Proceedings of the 9th International Symposium on Systems, Modeling and Control, SMC'98, Zakopane, Poland, April 27 - May 1, 1998.
• [49] A. Dzieliński. BIBO stability of approximate NARX models. Proceedings of the American Control Conference, ACC'99, s. 4000-4002, San Diego, California, June 2-4, 1999.
• [50] A. Dzieliński. BIBO stability of NARX models. Proceedings of the Mediterranean Control Conference, MED'99, s. 1198-1206, Haifa, Israel, June 26-28, 1999.
• [51] A. Dzieliński. BIBO stability of nonlinear systems. Proceedings of the European Control Conference, ECC'99, strona F0389, Karlsruhe, Germany, August 31 - September 3, 1999.
• [52] A. Dzieliński. Difference inequalities and stability of NARX models. Proceedings of the European Control Conference, ECC'99, s. I1068-6, Karlsruhe, Germany, August 31 - September 3, 1999.
• [53] A. Dzieliński. Neural networks based NARX models in nonlinear adaptve control. Proceedings of International Joint Conference on Neural Networks, IJ CNN'99, Washington, DC, July 10-16, 1999.
• [54] A. Dzieliński. NARX models application to model-based nonlinear control. Proceedings of 14th International Symposium of Mathematical Theory of Networks and Systems, MTNS'2000, Perpignan, France, June 19-23, 2000.
• [55] A. Dzieliński. Robust stability and control issues for NARX models. Proceedings of 3rd IFAC Symposium on Robust Control Design, ROCOND'2000, Prague, Czech Republic, June 21-23, 2000.
• [56] A. Dzieliński. Stability and control for N-D NARX models. Proceedings of the Second International Workshop on Multidimensional Systems, NDS'2000, s. 219-223, Czocha Castle, Poland, June 27-30, 2000.
• [57] A. Dzieliński. Approximate model application to geometric nonlinear control. Proceedings of 7th IEEE International Conference Methods and Models in Automation and Robotics, MMAR'01, s. 937-942, Międzyzdroje, Poland, August 28-31, 2001.
• [58] A. Dzieliński. MATLAB package for N-D sampling based modelling of nonlinear systems. K. Gałkowski, J. Wood, red., Multidimensional Signals, Circuits and Sy stems, s. 29-44. Taylor and Francis, London, 2001 .
• [59] A . Dzieliński. New models for geometric nonlinear control. Proceedings of 13th International Conference on Process Control, PC'01 , Štrbské Pleso, Slovakia, June 11-14, 2001.
• [60] H.G. Eggleston. Elementary Real Analysis. Cambridge University Press, Cambridge, 1962.
• [61] S. E. Fahlmann, C. Lebiere. The cascade-correlation learning architecture. D. S. Touretzky, red., Advances in Neural lnformation Processing Systems 2 , s. 524-532. Morgan Kaufmann Publishers, San Mateo, CA, 1990.
• [62] R. Fletcher. Practical Methods of Optimization. Second Edition. Wiley, Chichester, 1987.
• [63] H. Fritz. Neural speed control for autonomous road vehicles. Proceedings of the 2nd IFAC Conference on lntelligent Autonomous Vehicles, s. 285-290, Helsinki, Finland, 1995.
• [64] H. Fritz. Model-based neural distance control for autonomous road vehicles. Proceedings of the IEEE Symposium on lntelligent Vehicles, s. 29-34, Tokyo, Japan, 1996.
• [65] V. Fromion, S. Monaco, D. Normand-Cyrot. A link between input-output stability and Lyapunov stability. Systems & Control Letters, 27:243-248, 1996.
• [66] K. Funahashi, Y. Nakamura. Approximation of dynamical systems by continuous time recurrent neural networks. Neural Networks, 6:801-806, 1993.
• [67] K. Funahashi. On the approximate realization of continuous mappings by neural networks. Neural Networks, 2:183-192, 1989 .
• [68] P. J. Gawthrop, E. Ronco. Local model networks and self-tuning predictive control. Proceedings of the 4th IEEE Mediterranean Symposium on New Directions in Control and Automation , 1996 .
• [69] P. J. Gawthrop. Continuous-time local state local model networks. Proceedings of 1995 IEEE Conference on Systems, Man, and Cybernetics, s. 852-857, Vancouver, British Columbia, 1995. IEEE Press.
• [70] P. J. Gawthrop. Continuous-time local model networks. R. Żbikowsk.i, K. J. Hunt, red., Neural Adaptive Control Technology , World Scientific Series in Robotics and Intelligent Systems, vol. 15, s. 41-70. World Scientific, Singapore, 1996.
• [71] I. M. Gelfand, S. V. Fomin. Calculus of Variations . Prentice-Hall, Englewood Cliffs, N.J., 1963.
• [72] S. Geman, E. Bienenstock, R. Doursat. Neural networks and the bias/variance dilemma. Neural Computation, 4(1): 1-58, 1992.
• [73] F. Girosi, T. Poggio. Representation properties of networks: Kolmogorov's theorem is irrelevant Neural Computation, I :465-469, 1989.
• [74] R. Haber, H. Unbehauen. Structure identification of nonlinear dynamic systems-a survey on input/output approaches. Automatica , 26:651-677, 1990.
• [75] W. Hahn. Theory and Application of Liapunov's Direct Method. Prentice-Hall, Englewood Cliffs, NJ, 1963.
• [76] W. Hahn. Stability of Motion. Springer-Verlag, New York, 1967.
• [77] E. Hartman, J. D. Kee1er. Predicting the future: Advantages of semilocal units. Neural Computation, 3(4):566-578, 1991.
• [78] M. H. Hayes, J. H. McClellan. Reducible polynomials in two or more variables. Proceedings of the IEEE, 70(2):197-198, 1982.
• [79] R. Hecht-Nielsen. Kolmogorov's mapping neural network existence theorem. Proceedings of the International Joint Conference on Neural Networks, vol. 3, s. 11-14, New York, 1987. IEEE Press.
• [80] M. A. Henson, D. E. Seborg. Theoretical ana1ysis of unconstrained nonlinear model predictive control. International Journal of Control, 58(5): 1053-1080, 1993.
• [81] H. Hochstadt. The Functions of Mathematical Physics. Wiley-Interscience, New York, 1971.
• [82] K. Hornik, M. Stinchcombe, H. White. Multilayer feedforward networks are universal approximators. Neural Networks, 2:359-366, 1989.
• [83] I. M. Horowitz. Synthesis of Feedback Systems. Academic Press, New York and London, 1963.
• [84] T. Hrycej. Model-based training of control sequences in neural controllers. Neural Network World , 2:173-188, 1994.
• [85] T. Hrycej. Regelung von Prüfständen mit neuronalen Netzen. Automatisierung , 43:297-304, 1995.
• [86] T. Hrycej. Neurocontrol. Towards an Industrial Control Methodology. John Wiley & Sons, New York, 1997.
• [87] K.J. Hunt, R. Haas, M. Brown. On the functional equivalence of fuzzy inference systems and spline-based networks. International Journal of Neural Systems, 6(5):171-184, 1995.
• [88] K.J. Hunt, R. Haas, R. Murray-Smith. Extending the functional equivalence of radial basis function networks and fuzzy inference systems. IEEE Transactions on Neural Networks, 7(5):776-781, 1996.
• [89] K.J. Hunt, T.A. Johansen. Design and analysis of gain-scheduled control using local controller networks. International Journal of Control, 66(5):619-651, 1997.
• [90] K. J. Hunt, D. Sbarbaro, R. Żbikowski, P. J. Gawthrop. Neural networks for control systems: A survey. Automatica , 28(6):1083-1112, November 1992.
• [91] N. E. Hurt. Phase Retrieval and Zero Crossings. Mathematical Methods in Image Reconstruction. Kluwer Academic Publications, Dordrecht, Boston and London, 1989.
• [92] J. M. Hutchinson. Radial Basis Function Approach to Financial Time Series Analysis. Praca doktorska, Massachusetts Institute of Technology, Dept. EECS, February 1994.
• [93] F. J. Doylem, F. Allgöwer, M. Morari. A normal form approach to approximate input-output linearization for maximum phase nonlinear SISO systems. IEEE Trans. on Automatic Control , 41:305-309, 1996.
• [94] A. J. lsaksson, L. Ljung, J.-E. Stromberg. On recursive construction of trees as models of dynamical systems. 30th Conf on Decision & Control, Brighton, s. 1686-1687, 1991.
• [95] A. Isidori. Nonlinear Control Systems: An lntroduction. Springer-Verlag, New York, wydanie drugie, 1989.
• [96] A. Isidori. Nonlinear Control Systems: An lntroduction. Springer-Verlag, Berlin, wydanie trzecie,1995.
• [97] T.A. Johansen, K.J. Hunt. Approximate feedback linearisation using gain scheduling. Automatica, 1998.
• [98] T. A. Johansen, B. Foss. Constructing narmax models using armax models. International Journal of Control, 58:1125-1153, 1993.
• [99] T. A. Johansen. Operating regime based process modeling and identifitation. Praca doktorska, Department of Engineering Cybernetics, Norwegian lnstitute of Technology, University of Trondheim, Norway, 1994.
• [100] M. I. Jordan, R. A. Jacobs. Hierarchical mixtures of experts and the em algorithm. Technical Report 9301, MIT, Computational Cognitive Science, April 1993.
• [101] T. Kaczorek. Two-Dimensional Li near Systems . Springer-Verlag, Berlin, 1985.
• [102] J. C. Kalkkuhl, K. J. Hunt. Discrete-time neural model structures for continuous nonlinear systems: Fundamental properties and control aspects. R. Żbikowski, K. J. Hunt, red., Neural Adaptive Control Techno logy , World Scientific Series in Robotics and Intelligent Systems, vol. 15, s. 3-40. World Scientific, Singapore, 1996.
• [103) J. C. Kalkkuhl, E. Liceaga-Castro. Disturhance anenuation by discrete-time output feedback for uncertain nonlinear siso systems. 1995.
• [104] J. C. Kalkkuhl. On the stability of a two-degrees of freedom interna! model controller. 1996.
• [105] T. Kavli. Learning Principles in Dynamic Control. Praca doktorska, University of Oslo, 1992.
• [106] S. P. Kim, N. K. Bose. Reconstruction of 2-D bandlimited discrete signals from nonuniform samples. IEE Proceedings, Pt. F, 137:197-204, 1990.
• [107] S. P. Kim. Recursive Reconstruction of High-resolution Images from Multiframes . Praca doktorska, Department of Electrical Engineering, The Pennsylvania State University, University Park, PA, December 1989.
• [108] K. Knopp. Theory and Application of lnfinite Series. Dover Publications, New York, 1990.
• [109] A. N. Kolmogorov. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Dokl. Akad. Nauk SSSR, 114:953-956, 1957. (English translation: American Mathematical Society Translations, vol. 28).
• [110] J. Korbicz, A. Obuchowicz, D. Uciński. Sztuczne sieci neuronowe: podstawy i zastosowania. Akademicka Oficyna Wydawnicza PU, Warszawa, 1994.
• [111] E. B. Kosmatopoulos. M. M. Polycarpou, M. A. Christodoulou, P. A. Ioannou. High-order neural network structures for identification of dynamical systems. IEEE Transactions on Neural Networks , 6(2):422-431, 1995.
• [112] E. B. Kosmatopoulos. Recurrent High-Order Neural Network for Learning in Dynamic Environments. Praca doktorska, Department of Electronic & Computer Engineering, Technical University of Crete, Crete, Greece, 1995.
• [113] V. A. Kotelnikov. On the Transmission Capacity of "Ether" and Wire in Electrocommunications. lzd. Red. Upr. Svyazi RKKA, Moscow, 1933.
• [114] O. Kona. lnversion method in the discrete-time Nonlinear Control Systems Synthesis Problems . Springer-Verlag, London, 1995.
• [115] J. S. Kowalik, M. R. Osborne. Methods fo r Unconstrained Optimization Problems. Elsevier, New York, 1968.
• [116] V. Kůrková. Kolmogorov's theorem is relevant. Neural Computation, 3:617-622, 1991.
• [117] V. Kůrková. Kolmogorov's theorem and multilayer neural networks. Neural Networks , 5:501-506, 1992.
• [118] V. Lakshmikantham, S. Leela. Differential and lntegral lnequalities . Theory and Applications , vol. II: Functional, Partial, Abstract, and Complex Differential Equations. Academic Press, New York and London, 1969.
• [119] V. Lakshmikantham, S. Leela. Differential and lntegral lnequalities. Theory and Applications, vol. II: Functional, Partial, Abstract, and Complex Differential Equations. Academic Press, New York and London, 1969.
• [120] V. Lakshmikantham, S. Leela. Differential and lntegrallnequalities. Theory and Applications, vol. I: Ordinary Differential Equations. Academic Press, New York and London, 1969.
• [121] V. Lakshmikantham, D. Trigiante. Theory of Difference Equations: Numerical Methods and Applications. Academic Press, Boston, 1988.
• [122] V. Lakshmikantham. Differential systems and extension of Lyapunov's method. Michigan Mathematical Journal, 9:311-320, 1962.
• [123] V. Lakshmikantham. Notes on variety of problems of differential systems. Archive for Rational Mechanics and Analysis, 10:119-126, 1962.
• [124] M. M. Lavrentiev. Some lmproperly Posed Problems of Mathematical Physics. Springer Verlag, Berlin, Heidelberg and New York, 1967.
• [125] S. Lee, R. M. Kil. A Gaussian potential function netwerk with hierarchically self-organizing learning. Neural Networks, 4:207-224, 1991.
• [126] P. Lelong, L. Gruman. Entire Functions of Several Comp/ex Variables. Springer-Verlag, Berlin, 1986.
• [127] I. J. Leontaritis, S. A. Billings. Input-output parametric models for non-linear systems. part I: Deterministic non-linear systems. International Journal of Control, 41:303-328, 1985.
• [128] A. U. Levin, K. S. Narendra. Identification using feedforward networks. Neural Computation, 7(2):349-357, 1995.
• [129] B. Ja. Levin. Distribution of Zeros of Entire Functions. Translations of Mathematical Monographs, vol. 5. American Mathematical Society, Providence, RI, 1964.
• [130] E. Liceaga-Castro, J. C. Kalkkuhl, R. C. Linares. Disturbance attenuation by output feedback for uncertain nonlinear siso systems. 1994.
• [131] E. Liceaga-Castro, J. C. Kalkkuhl. Output feedback control for non-minimum phase nonlinear systems. 1995.
• [132] J. N. Lin, R. Unbehauen. On the realization of Kolmogorov's network. Neural Computation, 5: 18-20, 1993.
• [133] S. Lipschutz. Generał Topology. McGraw-Hill, New York, 1965.
• [134] L. Ljung, T. SOderstrtim. Theory and Practice of Recursive Identification. MIT Press, London, 1983.
• [135] L. Ljung. System Identification-Theory for the U ser. Prentice-Hall, Englewood Cliffs, New Jersey, USA, wydanie drugie, 1999.
• [136] G. G. Lorentz. Approximation of Functions. Holt, Reinhart and Winston, New York, 1966.
• [137] N. N. Luzin. On the method of approximate integration due to academician S. A. Chaplygin.Uspekhi matematicheskikh nauk, 6(6):3-27, 1951.
• [138] S. M. Makarov. A generalisation of fundamental Lyapunov's theorems on stability of motion. Izvestiya fiziko-matematicheskogo obshchestva pri Kazanskom gosudarstvennam universitete (Seriya 3 ), 10(3):139-159, 1938.
• [139] F. A. Marvasti. A Unified Approach to Zero-Crossings and Nonuniform Sampling. Nonuniform, Oak Park, Illinois, USA, 1987.
• [140] F. Marvasti. Nonuniform sampling. Robert J. Marks II, red., Advanced Topics in Shannon Sampling and Interpolation Theory. Springer Verlag, New York, 1993.
• [141] W.S. McCulloch, W. Pitts. A logical calculus of the ideas imminent in nervous activity. Bulletin of Mathematical Biophysics, 5: 115-133, 1943.
• [142] M. D. Mesarovic, D. Macko, Y. Takahara. Theory of Hierarchical, Multilevel Systems. Academic Press, 1970.
• [143] W.T. Miller, R.S. Sutton, P.J. Werbos. Neural Networks for Control. MIT Press, Cambridge, MA, 1991.
• [144] M. Minsky, S.A. Papert. Perceptrons. MIT Press, Cambridge, MA, 1969.
• [145] D. S. Mitrinović. Elementary lnequalities. Noordhoff, Groningen, 1964.
• [146] S. Monaco, D. Normand-Cyrot Minimum-phase nonlinear discrete-time systems and feedback stabilization. Proceedings of the 26th Conference on Decision and Control, s. 979-986, Los Angeles, CA, December 1987. IEEE.
• [147] S. Monaco, D. Normand-Cyrot Zero dynamics of sampled nonlinear systems. Systems and Control Letters, 11:229-234, 1988.
• [148] J. Moody, C. J. Darken. Fast 1earning in networks of locally-tuned processing units. Neural Computation, 1:281-294, 1989.
• [149] R. Murray-Smith, K.J. Hunt Local model architectures for nonlinear modelling and control. K.J. Hunt, G.W. lrwin, K. Warwick, red., Neural Network Engineering in Dynamic Control Systems, Advances in Industrial Control, s. 61-82. Springer-Verlag, Berlin, 1995.
• [150] R. Murray-Smith, T.A. Johansen. Loca1learning in local model networks. Proceedings of the 4th lEE International Conference on Artificial Neural Networks, s. 40-46, Cambridge, UK, June 1995. IEE.
• [151] R. Murray-Smith, D. Neumerkel, D. Sbarbaro-Hofer. Neural networks for modelling and control of a non-linear dynamic system. 7th IEEE Symposium on Intelligent Control, Glasgow, s. 404-409, 1992.
• [152] K. S. Narendra, A. M. Annaswamy. Stable Adaptive Systems. Prentice-Hall, Eglewood Cliffs, NJ, 1989.
• [153] K. S. Narendra, K. Parthasarathy. Identification and control of dynamical systems using neural networks. IEEE Transaction on Neural Networks, 1(1):4-27, 1990.
• [154] K. S. Narendra, K. Parthasarathy. Gradient methods for the optimization of dynamical systems containing neural networks. IEEE Transactions on Neural Networks, 2:252-262, 1991.
• [155] D. Neumerkel, R. Murray-Smith, H. Gollee. Modeling dynamic processes with clustered time delay neurons. Proc. International Joint Conference on Neural Networks, Nagoya, Japan, 1993.
• [156] H. Nijmeijer, A. van der Schaft Nonlinear Dynamical Control Systems. Springer-Verlag, New York, 1990.
• [157] M. Nørgaard, O. Ravn, N.K. Poulsen, L. K. Hansen. Neural Networks for Modeling and Control of Dynamic Systems. Springer Verlag, London, Berlin, Heidelberg, 2000.
• [158] H. Nyquist. Certain topics in telegraph transmission theory. Transactions of AIEE, 47:617-644, 1928.
• [159] A. Okabe, B. Boots, K. Sugihara. Spatial Tessellations. Concepts and Applications of Voronoi Diagrams. John Wiley & Sons, Chichester, 1992.
• [160] S. M. Omohundro. Bumptrees for efficient function, constraint and classification learning. R. P. Lippmann, J. E. Moody, D. S. Touretzky, red., Advances in Neural lnformation Processing Systems 3, s. 693-ó99. Morgan Kaufmann Publishers, San Franciso, CA, 1991.
• [161] W. F. Osgood. Lehrbuch der Funktionentheorie. Zweiter Band (Erste Lieferung). Teubner, Leipzig, Berlin, 1924. (w Niemczech).
• [162] S. Osowski. Sieci neuronowe w ujęciu algorytmicznym. Wydawnictwa Naukowo-Techniczne WNT, Warszawa, 1996.
• [163] B. G. Pachpatte. On some n-th order finite difference inequalities. Proceedings of the National Academy of Sciences. lndia, Section A, 40:235-240, 1970.
• [164] B. G. Pachpatte. Finite-difference inequalities and an extension of Lyapunov's method. Michigan Mathematical Journal, 18:385-391, 1971.
• [165] R. E. A. C. Paley, N. Wiener. Fourier Transforms in the Complex Domain. Colloquium Publications, vol. 19. American Mathematical Society, Providence, RI, 1934.
• [166] C. J. Pantaleón-Prieto, F. Díaz de Mańa, A. Figueiras-Vidal. On training RBF networks. Neural Networks and Their Industrial & Cognitive Applications, Nimes, France, s. 279-288, 1993.
• [167] A. Papoulis. The Fourier integral and its Applications. McGraw-Hill, New York, 1962.
• [168] A. Papoulis. Signal Analysis. McGraw-Hill, 1977. [ 1 69) D. P. Petersen, D. Middleton. Sampling and reconstruction of wave-number-limited functions in n-dimensional euclidean spaces. information and Control, 5:279-323, 1962.
• [170] J. Platt. A resource-allocating netwark for function interpolation. Neural Computation, 3(2):213-225, 1991.
• [171] T. Poggio, F. Girosi. Networks for approximation and 1earning. Proceedings of the IEEE, 78:1481-1497, 1990.
• [172] J. Quinlan. C4.5 Programs for Machine Learning. Morgan Kaufmann, 1993.
• [173] R. Rabczuk Elements of Differential Inequalities. Polish Scientific Pub1ishers, Warszawa, 1976.
• [174] J. Raipala, H. N. Koivo. Self-generating radial base netwark in fault diagnosis. International Conference on Automation, Robotics and Computer Vision, Singapore, vol. I, s. NW-3.2.1-NW-3.2.5, 1992.
• [175] A. A. G. Requicha. The zeros of entire functions: Theory and engineering applications. Proceedings of the IEEE, 68(3):308-328, 1980.
• [176] L. I. Ronkin. lntroduction to the Theory of Entire Functions of Several Variables. Translations of Mathematical Monographs, vol. 44. American Mathematical Society, Providence, RI, 1974.
• [177] M. Roscheisen, R. Hofmann, V. Tresp. Neural control for rolling mills: lncorporating domain theories to overcome data deficiency. Advances in Neural Information Processing, vol. 4, s. 659-666. Lawrence Erlbaum Associates, 1992.
• [178] F. Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65:386-408, 1958.
• [179] G. A. Rovithakis, M. A. Christodoulou. Model reference adaptive control of unknown plants using dynamic neural networks. Applied Mathematics and Computer Science, 4(3):433-446, 1994.
• [180] W. Rudin. Princip/es of Mathematical Analysis, Third Edition. McGraw-Hill, Auckland, 1976.
• [181] W. J. Rugh. Analytical framework for gain scheduling. IEEE Control Systems Magazine, 11:79-84, 1991.
• [182] D. Rutkowska, M. Piliński, L. Rutkowski. Sieci neuronowe, algorytmy genetyczne i systemy rozmyte. Państwowe Wydawnictwo Naukowe PWN, Warszawa, 1997.
• [183] I. W. Sandberg. Approximation theorems for discrete-time systems. IEEE Transactions on Circuits and Systems, 38:564-566, 1991.
• [184] I. W. Sandberg. The reconstruction of band-limited signals from nonuniformly spaced samples. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications, 4 1:64-66, 1994.
• [185] R. M. Sanner, J.-J. E. Slotine. Gaussian networks for direct adaptive control. IEEE Transactions on Neural Networks, 3:837-863, 1992.
• [186] D. Sbarbaro, D. Neumerkel, K.J. Hunt. Neural control of a steel rolling mili. IEEE Control Systems Magazine, 1 3(3):69-75, 1993.
• [187] D. Sbarbaro. Connectionist Feedforward Networks for Control of Nonlinear Systems. Praca doktorska, Department of Mechanical Engineering, Glasgow University, Glasgow, Scotland, October 1992.
• [188] B. V. Shabat. Introduction to Comp/ex Analysis. Part II: Functions of Several Variables. Transations of Mathematical Monographs, vol. 110. American Mathematical Society, Providence, RI, 1992.
• [189] J. S. Shamma, M. Athans. Analysis of gain scheduled control for nonlinear plants. IEEE Trans. On Automatic Control, 35:898-907, 1990.
• [190] J. S. Shamma, M. Athans. Gain scheduling: Potential hazards and possible remedies. IEEE Control Systems Magazine, s. 10 1-107, June 1992.
• [191] C. E. Shannon. Communication in the presence of noise. Proceedings of the !RE, 37:10--21, 1949.
• [192] D. Slepian. Some comments on Fourier analysis, uncertainty and modelling. SIAM Review, 25(3):379-393, July 1983.
• [193] I. N. Sneddon. Fourier Transforms. McGraw-Hill, New York, 1951.
• [194] S. L. Sobolev. Partial Differential Equations of Mathematical Physics. Pergamon Press, Oxford, 1964.
• [195] E. Sontag. Neural nets as systems models and controllers. Proc. Seventh Yale Workshop on Adaptive and Learning Systems, s. 73-79. Yale University, 1992.
• [196] D. F. Specht. A general regression neural network. IEEE Transactions on Neural Networks, 2(6), 1991.
• [197] D. A. Sprecher. On the structure of continuous functions of several variables. Transactions of the American Mathematical Society, 1 1 5:340-355, 1965.
• [198] E. M. Stein, G. Weiss. Introduction to Fourier Analysis on Euclidean Spaces. Princeton University Press, Princeton, NJ, 1971.
• [199] K. Stokbro, D. K. Umberger, J. A. Hertz. Exploiting neurons with localized receptive fields to team chaos. Complex Systems, 4(3):603-622, 1990.
• [200] M. H. Stone. The generalized Weierstrass approximation theorem. Mathematics Magazine, 21:167- 184, 237-254, 1948.
• [201] J. E. Strömberg, F. Gustafsson, L. Ljung. Trees as black-box model structures for dynamical systems. European Control Conference, Grenoble, s. 1175- 1 1 80, 1991.
• [202] A. H. Stroud. Approximate Calculation of Multiple lntegrals. Prentice-Hall, Englewood Clitfs, NJ, 1971.
• [203] J. Szarski. Differential inequalities. Polish Scientific Publishers, Warszawa, wydanie drugie, 1967.
• [204] R. Tadeusiewicz. Sieci neuronowe. Akademicka Oficyna Wydawnicza, Warszawa, 1993.
• [205] T. Takagi, M. Sugeno. Fuzzy identification of systems and its application to modeling and control. IEEE Trans. on Systems, Man, and Cybernetics, 15:116-132, 1985.
• [206] J. D. Talman. Special Functions. A Group Theoretic Approach. W. A. Benjamin, New York, Amsterdam, 1968.
• [207] A. N. Tikhonov, V. Y. Arsenin. Solution of Ill-posed Problems. John Wiley & Sons, New York, 1977.
• [208] M. J. van Nieuwstadt. Trajectory generation for nonlinear control systems. Praca doktorska, Department of Mechanical Engineering, California Institute of Technology, Pasadena, California, 1997.
• [209] M. Vidyasagar. Nonlinear Systems Analysis. Prentice-Hall, Englewood Clitfs, 1992.
• [210] A. G. Vitushkin. On Hilbert's thirteenth problem. Dokl. Akad. Nauk SSSR, 95:701-704, 1954.
• [211] W. Waller. Differential and lntegral inequalities. Springer-Verlag, Berlin, New York, 1970.
• [212] H. O. Wang, K. Tanaka, M.F. Griffin. An approach to fuzzy control of nonlinear systems: Stability and design issues. IEEE Transactions on Fuzzy Systems, 4:14-23, 1996.
• [213] E. T. Whittaker. On the functions which are represented by the expansions of the interpolation theory. Proc. Royal Society Edinbourgh, 35:181-194, 1915.
• [214] J. J. O. O. Wiegerinck. Growth properties of Paley-Wiener functions on C". Proceedings of the Koninklijke Nederlands Akademie van Wetenschappen, Series A: Mathematical Sciences, 87:95-112, 1984.
• [215] G. Zames. Input-output feedback stability and robustness. IEEE Control Systems Magazine, 16(3):61-66, 1996.
• [216] J. Zhao, V. Wertz, R. Gorez. Linear TS fuzzy model based robust stabilizing controller design. Proceedings of the IEEE Conference on Decision and Control, s. 255-260, New Orleans, LA, 1995.
• [217] R. Żbikowski, A. Dzie1ióski. Neural approximation: A control perspective. K. J. Hun t, G. R. Irwin, K. Warwick, red., Advances in Neural Network.s for Control Systems, Advances in Industrial Control. Springer-Verlag, Berlin, New York, 1995.
• [218] R. Żbikowski, A. Dzieliński. Fourier transform invariance and symmetry for neurocontrol of narma models. Proceedings of the Second World Congress of Nonlinear Analysis, WCNA-96, Athens, Greece, July 10-17 1996.
• [219] R. Żbikowski, A. Dzieliński. Nonuniform sampling approach to control systems modelling with feedforward neural networks. R. Żbikowski, K. J. Hunt, red., Neural Adaptive Control Technology, World Scientific Series in Robotics and lntelligent Systems, vol. 15, s. 71-1 12. World Scientific, Singapore, 1996.
• [220] R. Żbikowski, A. Dzieliński. Fourier transform symmetry and invariance for neurocontrol of NARMA models. Nonlinear Analysis, Methods and Applications, 30(4): 1985-1993, 1997.
• [221] R. Żbikowski, K. J. Hunt. A. Dzie1iński, R. Murray-Smith, P. J. Gawthrop. A review of advances in neural adaptive control systems. Technical Report of the ESPRIT NACT Project TP-1, Glasgow University and Daimler-Benz Research, 1994. (Available from FTP server ftp.mech.gla.ac.uk as PostScript file /nact/nact_tpl.ps).
• [222] R. Żbikowski. The problem of generic nonlinear control. Proc. IEEE/SMC International Conference on Systems, Man and Cybernetics, Le Touquet, France, vol. 4, s. 74-79, 1993.
• [223] R. Żbikowski. Recurrent Neural Networks: Some Control Problems. Praca doktorska, Department of Mechanical Engineering, Glasgow University, Glasgow, Scotland, May 1994.
• [224] J. Żurada, M. Barski, W. Jędruch. Sztuczne sieci neuronowe: podstawy teorii i zastosowania. Państwowe Wydawnictwo Naukowe PWN, Warszawa, 1996.