Adaptive Neuro-Fuzzy Structure Based Control Architecture

The purpose of this paper is to present a practical application of a Sugeno model based adaptive neuro-fuzzy architecture. The main challenge of the project was to realize the real-time control of the system and the real-time parameter adaptation of the controller. The neuro-fuzzy controller module is implemented using High Level Synthesis technique, and it's integrated into a microprocessor based architecture on a System on Chip (SoC) type integrated circuit. The architecture is used to control a two degrees of freedom system, which is composed of two horizontal arms attached to a linear bearing. The bearing is running on a vertical beam so the system can execute a vertical motion and a rotary motion around the vertical axle. The positions according to the two degrees of freedom are determined using an ultrasonic and a magnetic sensor.