Application of Knowledge-Based Systems and Fuzzy Logic to Automatic Control

Abstract

This thesis investigates the application of Knowledge Based systems and Fuzzy Logic to automatic control. The knowledge used by a human operator is put in a computer usable form and applied to a control problem. The idea is not to attempt to enhance the stability or response of the system but given a basically stable and controllable system we apply human type control methods via a computer controller. A system can never be modelled exactly and therefore a controller design must allow for the uncertainty in the model. With fuzzy logic, the system inputs, outputs, parameters, reactions and cross coupling are represented in fuzzy or inexact variables, knowledge and reasoning. An exact (or nearly exact) model of the system is not necessary. A simple aircraft is the process to which this control method is applied. Knowledge, reasoning and feedback similar to what a human pilot utilizes are applied in the control of the process.