Refining PID Controllers Using Neural Networks

The KBANN (Knowledge-Based Artificial Neural Networks) approach uses neural networks to refine knowledge that can be written in the form of simple propositional rules. We extend this idea further by presenting the MANNCON (Multivariable Artificial Neural Network Control) algorithm by which the mathematical equations governing a PID (Proportional-Integral-Derivative) controller determine the topology and initial weights of a network, which is further trained using backpropagation. We apply this method to the task of controlling the outflow and temperature of a water tank, producing statistically significant gains in accuracy over both a standard neural network approach and a nonlearning PID controller. Furthermore, using the PID knowledge to initialize the weights of the network produces statistically less variation in test set accuracy when compared to networks initialized with small random numbers.

[1]  Carlos E. Garcia,et al.  Internal model control. A unifying review and some new results , 1982 .

[2]  George Stephanopoulos,et al.  Chemical Process Control: An Introduction to Theory and Practice , 1983 .

[3]  B. Bavarian,et al.  Introduction to neural networks for intelligent control , 1988, IEEE Control Systems Magazine.

[4]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

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

[6]  Thomas J. Mc Avoy,et al.  Use of Neural Nets For Dynamic Modeling and Control of Chemical Process Systems , 1989, 1989 American Control Conference.

[7]  Jean-Jacques E. Slotine,et al.  Neural Network Control of Unknown Nonlinear Systems , 1989, 1989 American Control Conference.

[8]  Paul J. Werbos,et al.  Neural networks for control and system identification , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[9]  Judy A. Franklin,et al.  Historical perspective and state of the art in connectionist learning control , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[10]  M. Gori,et al.  BPS: a learning algorithm for capturing the dynamic nature of speech , 1989, International 1989 Joint Conference on Neural Networks.

[11]  Costas J. Spanos,et al.  Advanced process control , 1989 .

[12]  Michael I. Jordan,et al.  Learning to Control an Unstable System with Forward Modeling , 1989, NIPS.

[13]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[14]  Yaman Arkun,et al.  Neural Network Modeling and an Extended DMC Algorithm to Control Nonlinear Systems , 1990, 1990 American Control Conference.

[15]  Jude Shavlik,et al.  Refinement ofApproximate Domain Theories by Knowledge-Based Neural Networks , 1990, AAAI.

[16]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.

[17]  N. V. Bhat,et al.  Use of neural nets for dynamic modeling and control of chemical process systems , 1990 .

[18]  Roman W. Swiniarski.  Novel Neural Network based Self-Tuning PID Controller Which Uses Pattern Recognition Technique , 1990, 1990 American Control Conference.

[19]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[20]  Allon Guez,et al.  Two Degree of Freedom Robot Adaptive Controller , 1990, 1990 American Control Conference.

[21]  Jude W. Shavlik,et al.  Refining Domain Theories Expressed as Finite-State Automata , 1991, ML.

[22]  Allon Guez,et al.  ART based adaptive pole placement for neurocontrollers , 1991, Neural Networks.

[23]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[24]  T. Payne,et al.  Back propagation neural networks for facial verification , 1992 .