Abstract
Neural networks are developed by morphologically and computationally simulating a human brain. Although, as seen in previous chapters, the precise operation details of artificial neural networks are quite different from human brains, they are similar in three aspects. First, a neural network consists of a very large number of simple processing elements (the neurons). Second, each neuron is connected to a large number of other neurons. Third, the functionality of the networks is determined by modifying the strengths of connections during a learning phase [Psaltis et al, 1988; Hunt et al, 1992; Warwick et ai, 1992]. Efforts have been made to find efficient approaches for control from physiological studies of the brain. Research over the last twenty years has revealed the architecture and performance characteristics of the brain as a controller [Albus, 1975; Ito, 1984; Kawato et al, 1987] and has shown that neural network controllers have important advantages over conventional controllers. The first advantage is that a neural network controller can efficiently utilise a much larger amount of sensory information in planning and executing a control action than an industrial controller can. The second advantage is that a neural network controller has the collective processing capability that enables it to respond quickly to complex sensory inputs while the execution speed of sophisticated control algorithms in a conventional controller is severely limited.
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
Albus, J. S. (1975) A new approach to manipulator control: cerebellar model articulation control (CMAC), Trans. ASME, J. of Dynamics Syst., Meas. and Contr., 97, 220–227.
Albus, J. S. (1975) Data storage in the cerebellar model articulation controller (CMAC), Trans. ASME, J. of Dynamics Syst., Meas. and Contr., 97, 228–233.
Albus, J. S. (1979) A model ofthe brain for robot control, Byte, 54–95.
Albus, J. S. (1979) Mechanisms of planning and problem solving in the brain, Math. Biosci., 45, 247–293.
An, P.E., Brown, M., Harris, CJ., Lawrence, AJ., Moore, CJ. (1994) Associative memory neural networks: adaptive modelling theory, software implementations and graphical user, Engng. Appli. Arlif. Intell., 7(1), 1–21.
Astrom, KJ. and Wittenmark, B. (1989) Adaptive Control, Reading: Addison Wesley.
Bavarian, B. (1988) Introduction to neural networks for intelligent control, IEEE Contr. Syst. Mag., 3–7.
Colina-Morles, E. and Mort, N. (1993) Neural network-based adaptive control design, Journal of Systems Engineering, 2(1), 9–14.
Chen, F.E. (1990) Back propagation neural networks for nonlinear self tuning adaptive control, IEEE Contr. Syst. Mag., 44–48.
Evans, J.T., Gomm, J.B., Williams, D., Lisboa, P.J.G. and To, Q.S. (1993) A practical application of neural modelling and predictive control, in Page, G.F., Gomm, J.B. and Williams, D., Applications of Neural Networks to Modelling and Control, London: Chapman & Hall, 1993.
Guez, A. Eilbert, J.L. and Kam, M. (1988) Neural network architecture for control, IEEE Contr. Syst. Mag., 22–25.
Handelman, D. A., Lane, S. H. and Gelfand, J. J. (1989) Integrating neural networks and knowledge based systems for robotic control, Proc. 1989 IEEE Int. Conf. on Robotics and Auto., 3, 1454–460.
Hunt, KJ. and Sbarbaro, D. (1991) Neural networks for nonlinear internal model control, IEE Proceedings-D, 138(5), 431–438.
Hunt, K.J., Sbarbaro, D., Zbikowski, R. and Gawthrop, P.T. (1992) Neural networks for control systems - a survey, Automatica, 28(6), 1083–1112.
Ito, M. (1984) The cerebellar and neural control, New York: Raven Press. Kawato, M., Furukawa, K. and Suzuki, R. (1987) A hierarchical neural network model for control and learning of voluntary movement, BioL Cybern., 57, 169–185.
Kawato, M., Uno, Y., Isobe, M. and Suzuki, R (1988) Hierarchical neural network model for voluntary movements with application to robotics, IEEE Contr. Mag., 8–15.
Kraft, L. K. and Campagna, D. P. (1989) A comparison of CMAC neural network and traditional adaptive control systems, 1989 American Control Conference, Pittsburgh, PA, June 21-23, 1,884–889.
Kung, S.Y. and Hwang, IN. (1989) Neural network architectures for robotic applications, IEEE Tras. Robotics and Auto., 5(5),641–657.
Lee, T.H., Vue, P.K. and Tan, KK (1994) A neural-network-based model reference PID-like controller for process control, Eng. Applications of Artificial Intel, 7(6), 677–684.
Li, W. and Slotine, JJE. (1989) Neural network control of unknown nonlinear systems, 1989 American Control Conference, Pittsburgh, PA, June 21-23, 1136–1141.
Miller III, W.T., Glanz, F.H. and Kraft III, L.G. (1987) Application of a general learning algorithm to the control of robotic manipulators, Int. J. of Robotics Research, 6(2), 84–98.
Miller III, W. T. (1989) Real time application of neural networks for sensor based control of robots with vision, IEEE Trans. Syst. Man, and Cybern., 19(4), 825–831.
Miller III, W.T., Henes, RP., Glanz, F.H. and Kraft III, L.G. (1990) Real time dynamic control of an industrial manipulator using a neural network based learning controller, IEEE Trans. on Robotics and Automation, 6(1), 1–9.
Miller III, W.T., Glanz, F.H. and Kraft III, L.G. (1990) CMAC: An associative neural network alternative to backpropagation, Proc. of IEEE, 78(10), 1561–1567.
Miller III, W.T., Sutton, RS. and Werbos, P.J (eds) (1990) Neural Networksfor Control, Cambridge, MA: MIT Press.
Miyamoto, H., Kawato, M. Setoyama, T. and Suzuki, R (1988) Feedback error learning neural network for trajectory control of a robotic manipulator, Neural networks, 1,251–265.
Narendra, KS. and Parthasarathy, K (1990) Identification and control of dynamical systems using neural networks, IEEE Trans. on Neural Networks, 1(1),4–27.
Narendra, KS. and Parthasarathy, K (1991) Gradient methods for the optimization of dynamical systems containing neural networks, IEEE Trans. on Neural Networks, 2(2), 252–262.
Pham, D.T. and Liu, X. (1990) State space identification of dynamic systems using neural networks, Engineering Applications 0/ Artificial Intelligence, 3, 198–203.
Psaltis, D., Sideris, A. and Yamamura, A. A. (1988) A multilayered neural network controller, IEEE Control Systems Magazine, 17– 21.
Rovithakis, G.A. and Christodoulou, M.A. (1994) A robust direct adaptive regulation architecture using dynamic neural network models, Int. Conf. on System, Man and Cybernetics, San Antonio, Texas, USA, October 1994, 1110–1115.
Rumelhart, D. E. and McClelland, J L. (1986) Parallel Distributed Processing: explorations in the microstructure of cognition, vol.1: Foundations, MIT Press.
Saint-Donat, J, Bhat, N. and McAvoy, TJ. (1991) Neural net based model predictive control, Int. J. Control, 54(6), 1453–1468.
Walker, M., Haster, P. and Akers, L. (1989) A CMOS neural network for pattern association, IEEE MICRO, 9(5), 68–74.
Wang, H, Brown, M., Harris, C.J (1994) Fault detection for a class of unknown non-linear systems via associative memory networks, Proc. IMechE, Part I, J. 0/ Systems and Control Engineering, 208(12), 101–107.
Warwick, K, Irwin, G.W., Hunt, KJ (1992) Neural Networks/or Control and Systems, London: Peregrinus.
Werbos, PJ. (1991) An overview of neural networks for control, IEEE Control Systems Magazine, 40–41.
Werbos, PJ. (1991) Neural networks for modelling and optimization over time, Eighth Int. Conf. on Math. and Computer Modelling, Maryland, USA, 6.
Xu, L., Jiang, J.P. and Zhu, J. (1994) Supervised learning control of a nonlinear polymerisation reactor using the CMAC neural network for knowledge storage, Proc. IEE, Part D, 141(1), 33–38.
Yamada, T. and Yabuta, T. (1990) An extension of neural network direct controller, IEEE International Workshop on Intelligent Robots and Systems, July, Tsuchiura, Japan.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag London Limited
About this chapter
Cite this chapter
Pham, D.T., Liu, X. (1995). Neural Network Controllers. In: Neural Networks for Identification, Prediction and Control. Springer, London. https://doi.org/10.1007/978-1-4471-3244-8_6
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3244-8_6
Publisher Name: Springer, London
Print ISBN: 978-1-4471-3246-2
Online ISBN: 978-1-4471-3244-8
eBook Packages: Springer Book Archive