Robust control of nonlinear systems using pattern recognition

Pattern-recognition based methodology implemented in the architecture of artificial neural networks can be used to model knowledge-intensive feedback control systems. The procedure for development and practical design of a neural-net based control system is described and demonstrated by the example of a nonlinear hydraulic system. The neural-net control system has been trained to provide stabilizing controls and to detect and identify malfunctioning sensors. The results of computer simulations and experiments are presented to illustrate the proposed approach. They show that the neural-net control system is capable of maintaining any desired level of liquid in a tank, for tanks of various shapes; of stabilizing the system in the presence of large disturbances; of detecting and identifying defective level sensors; and of estimating parameters in nonlinear processes.<<ETX>>

[1]  Guy Albert Dumont,et al.  On PID controller tuning using orthonormal series identification , 1988, Autom..

[2]  J. G. Ziegler,et al.  Optimum Settings for Automatic Controllers , 1942, Journal of Fluids Engineering.

[3]  Dejan J. Sobajic,et al.  Increased effectiveness of learning by local neural feedback , 1988, Neural Networks.

[4]  Peter Wellstead,et al.  Pole assignment self-tuning regulator , 1979 .

[5]  Y.-H. Pao,et al.  A perspective on research aimed at understanding the systems nature of neural controllers , 1989, International 1989 Joint Conference on Neural Networks.

[6]  Yoh-Han Pao.  Engineering artificial intelligence , 1988 .

[7]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[8]  Tore Hägglund,et al.  Automatic Tuning of Simple Regulators for Phase and Amplitude Margins Specifications , 1983 .

[9]  T. R. Fortescue,et al.  Implementation of self-tuning regulators with variable forgetting factors , 1981, Autom..

[10]  Björn Wittenmark,et al.  On Self Tuning Regulators , 1973 .

[11]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[12]  Y. H. Pao,et al.  Characteristics of the functional link net: a higher order delta rule net , 1988, IEEE 1988 International Conference on Neural Networks.

[13]  A. Guez,et al.  Neural network architecture for control , 1988, IEEE Control Systems Magazine.

[14]  Tore Hägglund,et al.  Automatic tuning of simple regulators with specifications on phase and amplitude margins , 1984, Autom..

[15]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  Dale E. Seborg,et al.  A new method for on‐line controller tuning , 1982 .

[17]  B. Widrow,et al.  Stationary and nonstationary learning characteristics of the LMS adaptive filter , 1976, Proceedings of the IEEE.