Neural Computing for Numeric to Symbolic Conversion in Control Systems

Panos J. Antsaklis, K.M. Passino, and M.A. Sartori

1989 Control Systems Magazine
pp.44-52, April 1989

Abstract - Neural computing offers massively parallel computational facilities for the classification of patterns. In this paper, a certain type of neural network, called the multilayer perceptron; is used to classify numeric data and assign appropriate symbols to various classes. This numeric-to-symbolic conversion results in a type of “information extraction,” which is similar to uhat is called “data reduction” in pattern recognition. After introducing the idea of using the neural network as a numeric-to-symbolic converter, its use in autonomous control is discussed and several applications are studied. The perceptron is used as a numeric-to-symbolic converter for a discrete-event system controller supervising a continuous variable dynamic system. It is also shown how the perceptron can implement faultrees. which provide useful information (alarms) in a biological system and information for failure diagnosis and control purposes in an aircraft example.

[pdf file]