Abstract
Massively parallel arrays of simple processing elements, the so-called “neural” network models, can be used to greatly enhance and extend techniques for identification and control of complex, nonlinear dynamic systems. However, the design of practical algorithms capable of ensuring prespecified performance levels requires a comprehensive, cross-disciplinary treatment, drawing techniques and insights from such diverse fields as machine learning, constructive approximation, nonlinear dynamic stability, and robust systems analysis. The goal of this paper is to review techniques for assembling all of these elements into an integrated and systematic framework, highlighting both constructive neural network analysis and synthesis methods, as well as algorithms for adaptive prediction and control with guaranteed levels of performance. These designs also contain supervised network training methods as a special case, and hence provide tools for evaluating the quality of a training set, avoiding overtraining, and maximizing the speed of learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anderson, B. D. O., “Adaptive systems, lack of persistency of excitation and bursting phenomena”, Autom.atica, vol. 21, 247–258, 1985.
Annaswamy, A., and Seto, D., “Adaptive control of a class of nonlinear systems”, Proc. 7th Yale Workshop Adaptive and Learning Systems, New Haven, CT, May 1992.
Arsac, J., Fourier Transforms and the Theory of Distributions, Prentice-Hall, Englewood Cliffs, N.J., 1966.
Astrom, K. J., “Theory and applications of adaptive control: a survey”, Automatica, vol. 19, 471–486, 1983.
Astrom, K. J., and Wittenmark, B., Adaptive Control, Addison-Wesley, Reading, MA, 1989.
Atkeson, C. G., “Memory-based approaches to approximating continuous functions”, Proc. 6th Yale Workshop on Adaptive and Learning Systems, 212–217, Yale, New Haven, CT, 1990.
Atkeson, C. G., and Reinkensmeyer, D. J., “Using associative content-addressable memories to control robots”, in Neural Networks for Control, T.W. Miller, R.S. Sutton, and P.J. Werbos, eds., MIT Press, Cambridge, MA, 1990.
Bastin, G., Bitmead, R.R., Campion, G., and Gevers, M., “Identification of linearly overparameterized nonlinear systems”, IEEE Trans. Autom. Control, vol. 37, 1073–1078, July 1992.
Bellman, R., Adaptive Control Processes-A Guided Tour, Princeton University Press, Princeton, 1961.
Bracewell, R., The Fourier Transform and Its Applications, McGraw-Hill, New York, NY, 1965.
Broomhead, D. S., and Lowe, D., “Multivariable functional interpolation and adaptive networks”, Complex Systems,2, 321–355, 1988.
Butzer, P.L., Splettstosser and Stens, R.L., “The sampling theorem and linear prediction in signal analysis”, Jber. d., Dt. Math.-Verein, vol. 90, 1–70, 1988.
Chen, F.-C., and Khalil, H.K, “Adaptive control of nonlinear discrete-time systems using neural networks”, preprint Electrical Engineering Dept, Michigan State Univ., East Lansing, Mich, 1991.
Chen, S., Billings, S.A, and Grant, P.M., “Non-linear system identification using neural networks”, Int. J. Control, vol. 51, 1191–1214, 1990.
Chen, S., Cowan, C. F. N., Billings, S.A., and Grant, P.M., “Parallel recursive error prediction algorithm for training layered neural networks”, Intl. J. Control, vol. 51, 1215–1228, 1990.
Chen, S., Cowan, C. F. N., Billings, S.A., and Grant, P.M., “Practical identification of NARMAX models using radial basis functions”, Intl. J. Control, vol. 52, 1327–1350, 1990.
Chester, D., “Why two hidden layers are better than one”, IEEE Intl. Conf. on Neural Nets., I, 265–268, Washington, DC, 1990.
Chui, C. K., An Introduction to Wavelets, Academic Press, San Diego, 1992.
Cruz, Jr. J. B., System Sensitivity Analysis, Dowden,Hutchinson and Ross, Inc, Stroudsburg, PA, 1973.
Cybenko, G., “Approximations by superposition of a sigmoidal function”, Math. Cont., Sig, and Sys., vol. 2, 303–314, 1989.
Daugman, J. G., “Complete discrete 2D Gabor transforms by neural networks for image analysis and compression”, IEEE Trans. ASSP,36, 1169–1179, 1988.
Egardt, B., Stability of adaptive controllers, Springer-Verlag, Berlin, 1979.
Fu, K. S., “Learning control systems”, in Computer and Information Sciences, Julius Ton and Richard Wilcox, ed., Spartan Books, Washington, pp. 318–343, 1964.
Fu, K. S., and Waltz, M.D., “A heuristic approach to reinforcement-learning control systems”, IEEE Trans. Autom. Cont., vol. 10, 390–398, 1965.
Funahashi, K., “On the approximate realization of continuous mappings by neural networks”, Neural Networks,2, 183–192, 1989.
Gabor, D., “Theory of communication”, Jour. IEE, 93, 429–457, 1946.
Girosi, F. and Anzellotti, G. “ Rates of convergence of approximation by translates”, Artificial Intelligence Lab. Memo, No. 1288, MIT, Cambridge, MA, (in preparation), 1992.
Girosi, F., and Poggio, T., “Networks and the best approximation property”, Biological Cybernetics, vol 63, 169–176, 1990.
Girosi, F., and Poggio, T., “Representation properties of networks: Kolmogorov’s theorem is irrelevant”, Neural Computation, vol. 1, 465–469, 1989.
Goodwin, G. C., and Sin K. S., Adaptive Filtering, Prediction, and Control, Prentice-Hall, Englewood Cliffs, NJ, 1984.
Grossberg, S., Neural Networks and Natural Intelligence, MIT Press, Cambridge, MA, 1988.
Grossberg, S., “Nonlinear neural networks: principles, mechanisms, and architectures”, Neural Networks, vol. 1, 17–61, 1988.
Hebb, D.O., The Organization of Behavior, New York, Wiley, 1949.
Higgins, J.R., “Five short stories about the cardinal series”, Bull. Am. Math. Soc., vol. 12, 45–89, 1985.
Hopfield, J. J., “Neural networks and physical systems with emergent collective computational abilities”, Proc. Natl. Acad. Sci., USA, vol. 79, pp. 2554–2558, 1982.
Hopfield, J. J., “Neurons with graded response have collective computational properties like those of two-state neurons”, Proc. Natl. Acad. Sci., USA, vol. 81, pp. 3088–3092, 1984.
Hopfield, J. J., and Tank, D. W. ‘Neural’ computation of decisions in optimization problems“, Bio. Cybern., vol. 52, pp. 141–152, 1985.
Hornik, K., Stinchcombe, M., and White, H., “Multilayer feedforward networks are universal approximators”, Neural Networks,2, 359–366, 1989.
Hunt, K.J., Sbarbaro, D., Zbikowski, R., and Gawthrop, P.J., “Neural networks for control systems—a survey”, Automatica, vol. 28, 1083–1112, 1992.
Ioannou, P., and Datta, A., “Robust adaptive control: a unified approach”, Proc. IEEE,79, 12, pp. 1736–1768, Dec. 1991.
Ioannou, P., and Kokotovic, P.V., “Instability analysis and the improvement of robustness of adaptive control”, Automatica, 20,5, pp.583–594, Sept. 1984.
Isidori, A., Nonlinear Control Systems, Springer-Verlag, Berlin, 1989.
Jerri, A.J., “The Shannon sampling theorem—its various extensions and applications: a tutorial review”, Proc. IEEE, vol. 65, 1565–1596, 1977.
Jordan, M.I., “Learning inverse mappings using forward models”, Proc. 6th Yale Workshop on Adaptive and Learning Systems, 146–151, Aug. 1990.
Jordan, M. I., and Rumelhart, D.E., “Forward models: supervised learning with a distal teacher”, Cognitive Science, vol. 16, 307–354, 1992.
Kalman, R. E., “Design of a self-optimizing control system”, Trans. ASME,vol. 80, 468–478, 1958.
Kanellakopoulos, I., Kokotovic, P. V., Morse, A.S., “Systematic design of adaptive controllers for feedback linearizable systems”, IEEE Trans. Autom. Cont., vol. 36, 1241–1253, 1991.
Kohonen, T., Self-Organization and Associative Memory,Springer-Verlag, Berlin, 1984.
Kosko, B., Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ, 1992.
Kudva, P. and Narendra, K. S., “Synthesis of an adaptive observer using Lyapunov’s direct method”, Intl. J. Cont., vol. 18, 1201–1210, 1973.
Margolis, M. and Leondes, C. T., “On the theory of adaptive control systems: Method of teaching models”, Proc. 1st IFAC Congress, vol. 2, 1961.
Marks, R., J., Introduction to Shannon Sampling and Interpolation Theory, Springer-Verlag, New York, 1991.
McCulloch, W.S. and Pitts, W., “A logical calculus of ideas immanent in nervous activity”, Bull. Math. Biophys., vol. 5, pp.1115–1133, 1943.
Mendel, J.M., and McLaren, R.W., “Reinforcement-learning control and pattern recognition systems”, in Computer and Information Sciences, Julius Tou and Richard Wilcox, ed., Spartan Books, Washington, pp. 318–343, 1964.
Micchelli, C., “Interpolation of scattered data: distance matrices and conditionally positive definite functions”, Const. Approx., 2, pp. 11–22, 1986.
Miller, W. T., An, E., and Glanz, F., “The design of CMAC neural networks for control”, Proc. 6th Yale Workshop on Adaptive and Learning Systems, 218–224, Yale, New Haven, CT, 1990.
Miller, W. T., Glanz, F. H., and Kraft, L.G., “Application of a general learning algorithm to the control of robotic manipulators”, Intl. Jour. Rob. Res., 6, 84–98, 1987.
T.W. Miller, R.S. Sutton, and P.J. Werbos, eds., Neural Networks for Control, MIT Press, Cambridge, MA, 1990.
Minsky, M., and Papert, S., Perceptrons, MIT Press, Cambridge, MA, 1969.
Morse, A.S., “Global stablity of parameter adaptive systems”, IEEE Trans. Autom. Cont., vol. 25, 433–439, 1980.
Nam, K. and Arapostathis, “A model reference adaptive control scheme for pure-feedback nonlinear systems”, IEEE Trans. Autom. Control, 33, 9, 803–811, 1988.
Narendra, K. S., and Annaswamy, A., Stable Adaptive Systems, Prentice Hall, Englewood Cliffs, NJ, 1989.
Narendra, K.S., and Kudva, P., “Stable adaptive schemes for system identification and control—Parts I and IP”, IEEE Trans. Sys., Man, and Cyber., vol. SMC-4, 542–560, 1974.
Narendra, K.S., Lin, Y.H., and Valavani, L.S., “Stable adaptive controller design—Part II: proof of stability”,IEEE Trans. Autom. Cont., vol. 25, 440–448, 1980.
Narendra, K. S., and Parthasarathy, K., “Identification and control of dynamical systems using neural networks”, IEEE Trans. on Neural Networks, vol. 1, 4–27, 1990.
Narendra, K. S., and Parthasarathy, K., “Gradient methods for the optimization of dynamical systems containing neural networks”, IEEE Trans. on Neural Networks, vol. 2, 252–262, 1991.
Narendra, K. S., and Parthasarathy, K., “Identification and control of dynamical systems using neural networks—Part IP”, Proc. 6th Yale Workshop on Adaptive and Learning Systems, 164–172, Aug. 1990.
Narendra, K.S., and Valavani, L.S., “Stable adaptive controller design—Direct control”, IEEE Trans. Autom. Cont., vol. 23, 570–583, 1978.
Parks, P. C., “Lyapunov redesign of model reference adaptive control systems”, IEEE Trans. Autom. Control., vol. 11, 362–367, 1966.
Petersen, D. P., and Middleton, D., “Sampling and reconstruction of wave number limited functions in n-dimensional Euclidean spaces”, Information and Control, 5, 279–323, 1962.
Peterson, B. B., and Narendra, K. S., “Bounded Error Adaptive Control”, IEEE Trans. Autom. Cont.,27, 6, 1161–1168, 1982.
Poggio, T., and Girosi, F., “Networks for approximation and learning”, Proc. IEEE,78, 9, 1481–1497, 1990.
Poggio, T., and Girosi, F., “Extensions of a theory of networks for approximation and learning: dimensionality reduction and clustering”, Artificial Intelligence Lab. Memo, No. 1167, MIT, Cambridge, MA, April 1990.
Polycarpou, M., and loannou, P., “Identification and control of nonlinear systems using neural network models: design and stability analysis”, TR No. 91–09–01, USC Dept. EE-Systems, Sept. 1991.
Powell, M. J. D., “The theory of radial basis function approximation in 1990”, DA MTP Report, No. NA 11, Univ. of Cambridge, Cambridge, England, Dec. 1990.
Psaltis, D., Sideris, A., and Yamamura, A., “Neural Controllers”, Proc. 1st IEEE Conf. on Neural Networks, San Diego, CA, vol. IV, 551–557, June 1987
Rohrs, C., Valavani, L., Athans, M. and Stein, G., “Robustness of adaptive control algorithms in the presence of unmodelled dynamics”, Proc. 21st Conf. Dec. Control, 3–11, 1982.
Rosenblatt, F., Principles of Neurodynamics, Washington, Spartan Books, 1962.
Rumelhart, D. E., and McClelland, J. L., Parallel Distributed Processing, Explorations in the Microstructure of Cognition, vol. 1, MIT Press, Cambridge, MA, 1986.
Sadegh, N., “Nonlinear identification and control via neural networks”, ASME Winter Annual Meeting, pp. 45–56, 1991.
Sanner, R.M., “Stable adaptive control and recursive identification of nonlinear systems using radial gaussian networks”, Ph. D. Thesis, MIT Dept. of Aeronautics and Astronautics, May, 1993.
Sanner, R. M., and Slotine, J.-J. E., “Gaussian networks for direct adaptive control”, Proc. 1991 Automatic Control Conference, vol. 3, 2153–2159, Boston MA, June 1991.
Sanner, R. M., and Slotine, J.-J. E., “Gaussian networks for direct adaptive control”, IEEE Trans. Neural Networks, 3(6), pp 837–863, November 1992.
Sanner, R. M., and Slotine, J.-J. E., “Stable adaptive control and recursive identification using radial Gaussian networks”, IEEE Conf. Decision and Control,Brighton, England, December 1991.
Sauner, R. M., and Slotine, J.-J. E., “Enhanced algorithms for adaptive control using radial gaussian networks”, Proc. 1992 Automatic Control Conference, Chicago,IL,.June 1992.
Sanner, R. M., and Slotine, J.-J. E., “Stable recursive identification using radial basis function networks”, Proc. 1992 Automatic Control Conference, Chicago,IL, June 1992.
Sanner, R. M., and Slotine, J.-J. E., “Approximation error bounds for scattered-center Gaussian networks”, Proc. 1992 Conf. Dec. and Cont., Tuscon, AZ, Dec 1992.
Sastry, S., and Bodson, M., Adaptive Control: Stability, Convergence, and Robustness, Prentice-Hall, Englewood Cliffs, NJ, 1989.
Sastry, S., and Isidori, A. “Adaptive control of linearizable systems”, IEEE Trans. Autom. Control, 34, 1123–1131, 1989.
Schoenberg, I.J., “Metric spaces and positive definite functions”, Trans. Am. Math. Soc., 44, pp. 522–536, 1938.
Slotine, J.-J. E., “Sliding controller design for nonlinear systems”, Intl. Journal of Control, 40, 421, 1984.
Slotine, J.-J. E. and Coetsee, J.A., “Adaptive sliding controller synthesis for nonlinear systems”, Intl. Journal of Control, 1986.
Slotine, J.-J. E. and Li, W., “On the adaptive control of robotic manipulators”, Intl. Journal of Rob. Res., 6, 3, 1987.
Slotine, J.-J. E. and Li, W., Applied Nonlinear Control, Prentice Hall, Englewood Cliffs, NJ, 1991.
Sontag, E. D., “Feedback stabilization using two-hidden-layer networks”, IEEE Trans. Neural Networks, vol. 3, 981–990, 1992.
Strang, G., and Fix, G., “A Fourier analysis of the finite element variational method”, in Constructive Aspects of Functional Analysis, G. Geymonet, ed., 793–840, 1973.
Tsypkin, Ya. Z., Adaptation and Learning in Automatic Systems, Academic Press, New York, 1971.
Tzirkel-Hancock, E., and Fallside, F., “Stable control of nonlinear systems using neural networks”, Intl. J. Robust and Nonlinear Control,2, 63–86, May 1992.
Utkin, V. I., “Variable structure systems with sliding mode: a survey”, IEEE Trans. Auto. Contr., 22, 212, 1977.
Whittaker, E.T., “On the functions which are represented by the expansion of the interpolation theory”, Proc. Royal Soc. Edinburgh, vol. 35, 181–194, 1915.
Widrow, B., and Hoff, M. E., “Adaptive switching circuits”, Inst. Rad. Eng., WestCon Convention Record,IV, 96–104, 1960.
Widrow, B. and Smith, F. W, “Pattern-recognizing control systems”, in Computer and Information Sciences, Julius Tou and Richard Wilcox, ed., Spartan Books, Washington, pp. 318–343, 1964.
Winston, P. H., Artificial Intelligence, 3rd. ed., Addison-Wesley, Reading, MA, 1992.
Zaanen, A. C., Continuity, Integration, and Fourier Theory,Springer-Verlag, Berlin, 1989.
Zemanian, A. H., Distribution Theory and Transform Analysis,McGraw-Hill, New York, 1965.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer Science+Business Media New York
About this chapter
Cite this chapter
Slotine, JJ.E., Sanner, R.M. (1993). Neural Networks for Adaptive Control and Recursive Identification: A Theoretical Framework. In: Trentelman, H.L., Willems, J.C. (eds) Essays on Control. Progress in Systems and Control Theory, vol 14. Birkhäuser, Boston, MA. https://doi.org/10.1007/978-1-4612-0313-1_11
Download citation
DOI: https://doi.org/10.1007/978-1-4612-0313-1_11
Publisher Name: Birkhäuser, Boston, MA
Print ISBN: 978-1-4612-6702-7
Online ISBN: 978-1-4612-0313-1
eBook Packages: Springer Book Archive