×

Neural networks for control systems - a survey. (English) Zbl 0763.93004

Summary: This paper focuses on the promise of artificial neural networks in the realm of modelling, identification and control of nonlinear systems. The basic ideas and techniques of artificial neural networks are presented in language and notation familiar to control engineers. Applications of a variety of neural network architectures in control are surveyed. We explore the links between the fields of control science and neural networks in a unified presentation and identify key areas for future research.

MSC:

93A30 Mathematical modelling of systems (MSC2010)
93B30 System identification
93C10 Nonlinear systems in control theory
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Aarts, E.; Korst, J., ()
[2] Åström, K.J., Application of the robust and adaptive pole placement design technique, Int. J. of adaptive control and signal processing, 3, 167-189, (1989) · Zbl 0733.93045
[3] Åström, K.J.; Wittenmark, B., ()
[4] Ackley, D.H.; Hinton, G.H.; Sejnowski, T.J., A learning algorithm for Boltzmann machines, Cognitive science, 9, 147-169, (1985)
[5] Aizerman, M.A.; Braverman, E.M.; Rozonoer, L.I., Theoretical foundation of the potential function method in pattern recognition learning, Automatika i telemekhanika, 25, 1917-1936, (1964)
[6] Albert, A.E.; Gardner, L.A., ()
[7] Albus, J.S., Data storage in the cerebellar model articulation controller (CMAC), Trans. of the ASME, J. of dynamic systems, measurement, and control, 97, 228-233, (1975) · Zbl 0313.92006
[8] Albus, J.S., A new approach to manipulator control: the cerebellar model controller (CMAC), Trans. of the ASME, J. of dynamic systems, measurement, and control, 97, 220-227, (1975) · Zbl 0314.92007
[9] Almeida, L.B., Backpropagation in perceptrons with feedback, ()
[10] Anderson, B.D.O.; Bitmead, R.R.; Johnson, C.R.; Kokotovic, P.V.; Kosut, R.L.; Mareels, I.M.Y.; Praly, L.; Reidle, B.D., ()
[11] Anderson, C.W., Learning to control an inverted pendulum using neural networks, IEEE control systems magazine, 9, 31-37, (1989)
[12] Anderson, J.A.; Rosenfeld, E., ()
[13] Atkenson, C.G.; Reinkensmeyer, D.J., Using associative content-addressable memories to control robots, (), 1859-1864
[14] Ballard, D.H., Cortical connections and parallel processing: structure and function, (), 563-621
[15] Barron, A.R., Approximation and estimation bounds for artificial neural networks, (), 243-249
[16] Barto, A.G., An approach to learning control surface by connectionist systems, (), 665-701
[17] Barto, A.G., (), 5-58, Chapter 1
[18] Barto, A.G.; Sutton, R.S.; Anderson, Ch.W., Neuronlike adaptive elements that can solve difficult learning control problems, IEEE trans. on system, man, and cybernetics, 13, 834-846, (1983)
[19] Bassi, D.F., Connectionist dynamic control of robotic manipulators, ()
[20] Bassi, D.F.; Beckey, G.A., Decomposition of neural network model of robot dynamics: a feasibility study, Simulation and AI, 220, 8-13, (1989)
[21] Bavarian, B., Introduction to neural networks for intelligent control, IEEE control systems magazine, 8, 3-7, (1988)
[22] Bhat, N.V.; McAvoy, T.J., Use of neural nets for dynamical modelling and control of chemical process systems, Computers chem. engng., 14, 573-5583, (1990)
[23] Bhat, N.V.; Minderman, P.A.; McAvoy, T.; Wang, N.S., Modeling chemical process systems via neural computation, IEEE control systems magazine, 10, 24-29, (1990)
[24] Billings, S.A., Introduction to nonlinear system analysis and identification, () · Zbl 0588.93017
[25] Broomhead, D.S.; Lowe, D., Multivariable functional interpolation and adaptive networks, Complex systems, 2, 321-355, (1988) · Zbl 0657.68085
[26] Bruck, J., Computing with networks of threshold elements, ()
[27] Bullock, D., How neural networks factor problems of sensory motor control, (), 2271-2275
[28] Burkill, J.C.; Burkill, H., ()
[29] Carrol, M.S.; Dickinson, B.W., Construction of neural nets using the Radon transform, ()
[30] Casdagli, M., Non-linear system prediction of chaotic time series, Physica D, 35, 335-356, (1989) · Zbl 0671.62099
[31] Chen, Fu-Chuang, Back-propagation neural network for nonlinear self-tuning adaptive control, (), 274-279
[32] Chen, S.; Billings, S.A.; Cowan, C.F.; Grant, P.M., Practical identification of NARMAX models using radial basis functions, Int. J. control, 52, 1327-1350, (1990) · Zbl 0707.93075
[33] Chen, S.; Billings, S.A.; Grant, P.M., Non-linear system identification using neural networks, Int. J. control, 51, 1191-1214, (1990) · Zbl 0703.93071
[34] Chen, S.; Cowan, C.F.N.; Billings, S.A.; Grant, P.M., Parallel recursive prediction error algorithm for training layered neural networks, Int. J. control, 51, 1215-1228, (1990)
[35] Chen, V.C.; Pao, Y.H., Learning control with neural networks, (), 1448-1453
[36] Chen, V.C., Problem-solving by using reinforcement learning neural nets, (), 583-586
[37] Cheok, K.C.; Huang, N.J., Lyapunov stability analysis for self-learning neural model with application to semiactive suspension control system, (), 329-331
[38] Chester, D., Why two hidden layers are better than one, (), 265-268
[39] Chi, S.R.; Shoureshi, R.; Tenorio, M., Neural networks for system identification, IEEE control systems magazine, 10, 31-34, (1990)
[40] Chua, L.O.; Yang, L., Cellular neural networks: applications, IEEE trans. on circuits and systems, 35, 1273-1290, (1988)
[41] Chua, L.O.; Yang, L., Cellular neural networks: theory, IEEE trans. on circuits and systems, 35, 1257-1272, (1988) · Zbl 0663.94022
[42] Ciliz, M.K.; Isik, C., Time optimal control of mobile robot motion using neural nets, (), 368-373
[43] Cluett, W.R.; Shah, S.L.; Fisher, D.G., Robustness analysis of discrete-time adaptive control systems using input-output stability theory: A tutorial, (), 133-141 · Zbl 0639.93005
[44] Cohen, M.A.; Grossberg, S., Absolute stability of global pattern formation and parallel memory storage by competitive neural networks, IEEE trans. on system, man, and cybernetics, 13, 815-826, (1983) · Zbl 0553.92009
[45] Cybenko, G., Continuous valued networks with two hidden layers are sufficient, ()
[46] Cybenko, G., Approximation by superpositions of a sigmoidal function, Math. control signal systems, 2, 303-314, (1989) · Zbl 0679.94019
[47] Daunicht, W.J., Defanet—a deterministic approach to function approximation by neural networks, (), 161-164
[48] Demircioglu, H.; Gawthrop, P.J., Continuous-time relay self-tuning control, Int. J. control, 47, 1061-1080, (1988) · Zbl 0663.93045
[49] Ditto, W.L.; Rauseo, S.N.; Spano, M.L., Experimental control of chaos, Physical review letters, 65, 3211, (1990)
[50] Dzieliński, A.; Skoneczny, S.; Żbikowski, R.; Kukliński, S., Cellular neural network application to moiré pattern filtering, ()
[51] Economou, C.G.; Morari, M.; Palsson, B.O., Internal model control. 5. extension to nonlinear systems, Ind. eng. chem. process des. dev., 25, 403-411, (1986)
[52] Ersü, E.; Tolle, H., A new concept for learning control inspired by brain theory, (), 245-250
[53] Eykhoff, P., ()
[54] Fang, Y.; Sejnowski, T.J., Faster learning for dynamic recurrent backpropagation, Neural computation, 2, 270-273, (1990)
[55] Farmer, D.; Sidorowich, J., Predicting chaotic time series, Physical review letters, 59, 845, (1987)
[56] Fletcher, R., ()
[57] Franklin, J.A., Input space representation for refinement learning control, (), 115-122
[58] Fu, K.S., Learning control systems—review and outlook, Trans. IEEE on aut. control, 16, 210-221, (1970)
[59] Funahashi, K.I., On the approximate realization of continuous mappings by neural networks, Neural networks, 2, 183-192, (1989)
[60] Garcia, C.E.; Morari, M., Internal model control—1. A unifying review and some new results, Ind. eng. chem. process des. dev., 21, 308-323, (1982)
[61] Gawthrop, P.J., Robust stability of a continuous-time self-tuning controller, Int. J. of adaptive control and signal processing, 1, 31-48, (1987) · Zbl 0732.93054
[62] Gawthrop, P.J., Robust stability of multi-loop continuous-time self-tuning controllers, Int. J. of adaptive control and signal processing, 4, 359-382, (1990) · Zbl 0727.93041
[63] Gawthrop, P.J.; Sbarbaro, D.G., Stochastic approximation and multilayer perceptrons: the gain back-propagation algorithm, Complex system J., 4, 51-74, (1990) · Zbl 0713.68043
[64] Giles, C.L.; Maxwell, T., Learning, invariance, and generalization in high-order neural networks, Applied optics, 26, 4972-4978, (1987)
[65] Girosi, F.; Poggio, T., Representation properties of networks: Kolmogorov’s theorem is irrelevant, Neural computation, 1, 465-469, (1989)
[66] Girosi, F.; Poggio, T., Networks and the best approximation property, Biological cybernetics, 63, 169-176, (1990) · Zbl 0714.94029
[67] Goldberg, K.; Pearlmutter, B.A., Using a neural network to learn the dynamic of the CMU direct-drive arm II, (), 1988
[68] Goodwin, G.C.; Sin, K.S., ()
[69] Graf, D.H.; Lalonde, W.R., A neural controller for collision-free movement of general robot manipulators, (), 77-84
[70] Grant, E.; Zhang, B., A neural net approach to supervised learning of pole balancing, (), 123-129
[71] Grossberg, S., Adaptive pattern classification and universal recording: I. parallel development and coding of neural feature detectors, Biological cybernetics, 23, 121-134, (1976) · Zbl 0339.92004
[72] Grossberg, S., ()
[73] Guez, A.; Elibert, J.L.; Kam, M., Neural network architecture for control, IEEE control systems magazine, 8, 22-25, (1988)
[74] Guez, A.; Selinsky, J.W., A neurocontroller with guaranteed performance for rigid robots, (), 347-350
[75] Guhua, A.; Mathur, A., Setpoint control based on reinforcement learning, (), 511-514
[76] Haber, R.; Unbehauen, H., Structure identification of nonlinear dynamic systems—A survey on input/output approaches, Automatica, 26, 651-677, (1990) · Zbl 0721.93023
[77] Hartman, E.; Keeler, J.D., Predicting the future with semi-local units, Neural computation, (1992), To appear
[78] Hebb, D.O., ()
[79] Hecht-Nielsen, R., Counterpropagation networks, Applied optics, 26, 4979-4984, (1987)
[80] Hecht-Nielsen, R., Kolmogorov’s mapping neural network existence theorem, ()
[81] Hecht-Nielsen, R., Neurocomputer applications, (), 445-453
[82] Helferty, J.J.; Collins, J.B.; Kam, M., A neural network learning strategy for the control of a one-legged hopping machine, (), 1604-1609
[83] Hopfield, J.J., Neural networks and physical systems with emergent collective computational abilities, (), 2554-2558 · Zbl 1369.92007
[84] Hopfield, J.J., Neurons with graded response have collective computational properties like those of two-state neurons, (), 3088-3092 · Zbl 1371.92015
[85] Hornik, K.; Stinchcombe, M.; White, H., Multilayer feedforward networks are universal approximators, Neural networks, 2, 359-366, (1989) · Zbl 1383.92015
[86] Hunt, K.J.; Sbarbaro, D., Neural networks for non-linear internal model control, (), 431-438 · Zbl 0755.93034
[87] IEEE, Special issue on neural networks, IEEE control systems magazine, 8, (1988)
[88] IEEE, Special issue on neural networks, IEEE control systems magazine, 9, (1989)
[89] IEEE, Special issue on neural networks, IEEE control systems magazine, 10, (1990)
[90] Johanson, R., Real-time identification of multilinear systems, (), 119-123
[91] Johnson, J.L., Globally stable saturable learning laws, Neural networks, 4, 47-51, (1991)
[92] Jordan, M.I.; Rumelhart, D.E., Forward models: supervised learning with a distal teacher, (), 49, (submitted to “Cognitive Science”)
[93] Josin, G., Neural-space generalization of a topological transformation, Biological cybernetics, 59, 283-290, (1988) · Zbl 0652.92007
[94] Josin, G.M., Development of a neural network autopilot model for high performance aircraft, (), 547-550
[95] Karsai, G.; Anderson, K.; Cook, G.; Ramaswamy, K., Dynamic modelling and control of nonlinear process using neural network techniques, (), 280-286
[96] Kawato, M.; Uno, Y.; Isobe, M.; Suzuki, R., Hierarchical neural network model for voluntary movement with application to robotics, IEEE control systems magazine, 8, 8-17, (1988)
[97] Keerthi, S.S.; Gilbert, E.G., Moving-horizon approximations for a general class of optimal nonlinear infinite-horizon discrete-time systems, (), 301-306 · Zbl 0622.93044
[98] Kelly, D.G., Stability in contractive nonlinear neural networks, IEEE trans. on biomedical engineering, 37, 231-242, (1990)
[99] Kohonen, T., ()
[100] Kollias, S.; Anastassiou, D., An adaptive least squares for efficient training of artificial neural networks, IEEE trans. on circuits and systems, 36, 1092-1101, (1989)
[101] Kolmogorov, A.N., On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition, Dokl. akad. nauk SSSR, 114, 953-956, (1957) · Zbl 0090.27103
[102] Kosikov, V.S.; Kurdyukov, A.P., Design of a nonsearching self-adjusting system for nonlinear plant, Automatika i telemekhanika, 4, 58-65, (1987) · Zbl 0629.93040
[103] Kosut, R.L.; Friedlander, B., Robust adaptive control: conditions for global stability, IEEE trans. on aut. control, AC-30, 610-624, (1985) · Zbl 0563.93042
[104] Kosut, R.L.; Johnson, C.R., An input-output view of robustness in adaptive control, Automatica, 20, 569-582, (1984) · Zbl 0546.93049
[105] Kraft, L.G.; Campagna, D.P., A comparison between CMAC neural network control and two traditional adaptive control systems, IEEE control systems magazine, 10, 36-43, (1990)
[106] Kumar, S.; Guez, A., Adaptive pole placement for neurocontrol, (), 397-400
[107] Kurkova, V., Kolmogorov’s theorem is relevant, Neural computation, 3, 617-622, (1991)
[108] Lane, S.H.; Handelman, D.A.; Gelfand, J.J., Higher order CMAC neural networks—theory and practice, (), 1579-1585
[109] Lapedes, A.; Farber, R., Non-linear signal processing using neural networks: prediction and system modelling, ()
[110] Lee, Chuen-Chien; Berenji, H.R., An intelligent controller based on approximate reasoning and reinforcement learning, (), 200-205
[111] Li, J.H.; Michel, A.N.; Porod, W., Qualitative analysis and synthesis of a class of neural networks, IEEE trans. on circuits and systems, 35, 976-986, (1988) · Zbl 0664.34042
[112] Lin, J.; Unbehauen, R., Adaptive nonlinear digital filter with canonical piecewise-linear structure, IEEE trans. on circuits and systems, 37, 347-353, (1990)
[113] Lippmann, R.P., An introduction to computing with neural nets, IEEE ASSP magazine, 4, 4-22, (1987)
[114] Ljung, L., ()
[115] Ljung, L.; Söderström, T., ()
[116] Lorentz, G.G., (), 419-430
[117] Martinez, T.M.; Ritter, H.; Schulten, K.J., Three-dimensional neural net for learning visuomotor-coordination of a robot arm, (), 351-356
[118] Mayne, D.Q.; Michalska, H., Receding horizon control of nonlinear systems, Trans. IEEE on aut. control, 35, 814-824, (1990) · Zbl 0715.49036
[119] McCulloch, W.S.; Pitts, W., A logical calculus of the ideas immanent in nervous activity, Bulletin of mathematical biophysics, 9, 127-147, (1943) · Zbl 0063.03860
[120] Metropolis, N.; Rosenbluth, A.; Rosenbluth, M.; Teller, A.; Teller, E., Equation of state calculations by fast computing machines, J. chemical physics, 21, 1087-1092, (1953)
[121] Michel, A.N.; Farrell, J.A.; Porod, W., Qualitative analysis of neural networks, IEEE trans. on circuits and systems, 36, 229-243, (1989) · Zbl 0672.94015
[122] Miller, W.T.; Glanz, F.H.; Kraft, L.G., Application of a general learning algorithm to the control of robotic manipulators, The int. J. of robotic research, 6, 84-98, (1987)
[123] Miller, W.T.; Sutton, R.S.; Werbos, P.J., ()
[124] Minsky, M.L.; Papert, S.A., ()
[125] Minsky, M.L.; Papert, S.A., ()
[126] Moody, J.; Darken, C., Fast-learning in networks of locally-tuned processing units, Neural computation, 1, 281-294, (1989)
[127] Morari, M.; Zafiriou, E., ()
[128] Narendra, K.S., (), 115-142, Chapter 5
[129] Narendra, K.S.; Annaswamy, A.M., ()
[130] Narendra, K.S.; Parthasarathy, K., Identification and control for dynamic systems using neural networks, IEEE trans. on neural networks, 1, 4-27, (1990)
[131] Ott, E.; Grebori, C.; Yorke, J.A., Controlling chaos, Physical review letters, 64, 1196, (1990) · Zbl 0964.37501
[132] Park, J.; Lee, S., Neural computation for collision-free path planning, ()
[133] Pearlmutter, B.A., Learning state space trajectories in recurrent neural networks, (), 1988
[134] Pearlmutter, B.A., Learning state space trajectories in recurrent neural networks, Neural computation, 1, 263-269, (1989)
[135] Pearlmutter, B.A., Dynamic recurrent neural networks, ()
[136] Pineda, F.J., Generalization of back-propagation to recurrent neural networks, Physical review letters, 59, 2229-2232, (1987)
[137] Pineda, F.J., Recurrent backpropagation and the dynamical approach to adaptive neural computation, Neural computation, 1, 161-172, (1989)
[138] Poggio, T., (), 128-153
[139] Poggio, T.; Girosi, F., Networks for approximation and learning, (), 1481-1497 · Zbl 1226.92005
[140] Porcino, D.P.; Collins, J.C., An application of neural networks to the guidance of free-swimming submersibles, (), 417-420
[141] Poteryaiko, I.Y., On Liapunov function for neural networks models with multi-unit interaction, (), 21-23
[142] Psaltis, D.; Sideris, A.; Yamamura, A.A., A multilayered neural network controller, IEEE control systems magazine, 8, 17-21, (1988)
[143] Ritter, H.; Schulten, K., Topology conserving mappings for learning motor tasks, (), 376-380
[144] Ritter, H.; Schulten, K., Extending Kohonen’s self-organizing mapping algorithm to learn ballistic movements, (), 393-406
[145] Robinson, A.J., Dynamic error propagation networks, ()
[146] Robinson, A.J.; Fallside, F., Static and dynamic error propagation networks with application to speech coding, (), 1987
[147] Rohrs, C.E.; Valavani, L.S.; Athans, M.; Stein, G., Robustness of continuous-time adaptive control in the presence of unmodeled dynamics, Trans. IEEE, AC-30, 881-889, (1985) · Zbl 0571.93042
[148] Rosenblatt, F., The perceptron: a probabilistic model for information storage and organization in the brain, Psychological review, 65, 386-408, (1958)
[149] Rudin, W., ()
[150] Rumelhart, D.E.; Hinton, G.E.; Williams, R.J., Learning internal representations by error propagation, ()
[151] Rumelhart, D.E.; McClelland, J.L., ()
[152] Sanner, R.M.; Akin, D.L., Neuromorphic pitch attitude regulation of an underwater telerobot, IEEE control systems magazine, 10, 62-67, (1990)
[153] Sastry, S.S.; Bodson, ()
[154] Sato, M, Real time learning algorithm for recurrent analog neural networks, Biological cybernetics, 62, 237-241, (1990) · Zbl 0686.92010
[155] Savic, M.; Tan, Seow-Hwee, A new class of neural networks suitable for intelligent control, (), 418-423
[156] Sbarbaro, D.G.; Gawthrop, P.J., Self-organization and adaptation in Gaussian networks, (), 454-459
[157] Scalero, R.S.; Tepedelenlioglu, N., A fast algorithm for neural networks, (), 77-84
[158] Sekiguchi, M.; Nagata, S.; Asakawa, K., Behaviour control for mobile robot by multi-hierachical neural network, (), 1578-1583
[159] Shamma, S., Spatial and temporal processing in central auditory networks, (), 247-289
[160] Söderström, T.; Stoica, P., ()
[161] Sudharsanan, S.I.; Sundareshan, M.K., Equilibrium uniqueness and global exponential stability of a neural network for optimization applications, ()
[162] Tan, S.; Vandenberghe, L.; Vandewalle, J., Remarks on the stability of asymmetric dynamical neural networks, ()
[163] Troudet, T.; Merril, W., Neoromorphic learning continuous valued mappings in presence of noise, (), 312-319
[164] Tsypkin, Ya.Z, ()
[165] Ungar, L.H.; Powell, B.A.; Kamens, S.N., Adaptive networks for fault diagnosis and process control, Computers chem. engng., 14, 561-572, (1990)
[166] Weigand, A.S.; Huberman, B.A.; Rumelhart, D.E., Predicting the future: a connectionist approach, Int. J. neural systems, 3, 193, (1990)
[167] Werbos, P.J., Beyond regression: new tools for prediction and analysis in the behavior sciences, ()
[168] Werbos, P.J., Maximizing long-term gas industry profits in two minutes in lotus using neural network methods, IEEE trans. on systems, man, and cybernetics, 19, 315-333, (1989)
[169] Werbos, P.J., Backpropagation through time: what it does and how to do it?, (), 1550-1560
[170] Widrow, B., Adaptive inverse control, (), 1-5
[171] Widrow, B.; Hoff, M.E., Adaptive switching circuits, 1960 IRE WESCON convention record, New York: IRE, 96-104, (1960)
[172] Widrow, B.; Lehr, M.A., 30 years of adaptive neural networks: perceptron, medaline, and backpropagation, (), 1415-1441
[173] Widrow, B.; Stearns, S.D., ()
[174] Widrow, B.; Winter, R., Neural nets for adaptive filtering and adaptive pattern recognition, IEEE computer, 21, 25-39, (1988)
[175] Wiener, N., ()
[176] Williams, R.J.; Zipser, D., Experimental analysis of the real-time recurrent learning algorithm, Connection science, 1, 87-111, (1989)
[177] Williams, R.J.; Zipser, D., A learning algorithm for continually running fully recurrent neural networks, Neural computation, 1, 270-280, (1989)
[178] Williams, R.J.; Zipser, D., Gradient-based learning algorithms for recurrent connectionist networks, (), College of Computer Science
[179] Willis, M.J.; Di Massimo, C.; Montague, G.A.; Tham, M.T.; Morris, A.J., On artificial neural networks in process engineering, (), 256-266
[180] Wolfram, S., ()
[181] International Workshop. Cellular neural networks and their applications. Proc. CNNA’90.
[182] Ydstie, B.E., Forecasting and control using adaptive connectionist networks, Computers chem. engng., 14, 583-599, (1990)
[183] Yeung, D.Y.; Beckey, G.A., Using a context-sensitive learning network for robot arm control, (), 1441-1447
[184] Zak, S.H., Robust tracking control of dynamic systems with neural networks, (), 563-566
[185] Zhao, X.; Mendel, J., An artificial neural minimum-variance estimator, (), 499-506
[186] Zipser, D., A subgrouping strategy that reduces complexity and speeds up learning in recurrent networks, Neural computation, 1, 552-558, (1989)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.