Refining pid controllers using neural networks

Authors:
Gary M. Scott;Jude W. Shavlik;W. Harmon Ray
Affiliations:
Department of Chemical Engineering, University of Wisconsin, Madison, WI 53706 USA;Department of Computer Sciences, University of Wisconsin, Madison, WI 53706 USA;Department of Chemical Engineering, University of Wisconsin, Madison, WI 53706 USA
Venue:
Neural Computation
Year:
1992

Citing 2
Cited 1

Neural networks for control

Neural networks for control
Learning to control an unstable system with forward modeling

Advances in neural information processing systems 2

Connectionist theory refinement: genetically searching the space of network topologies

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.