Artificial neural network and PID based control system for DC motor drives

Abstract

This paper presents the design and implementation of a control system for permanent magnet motors using PID and artificial neural network controllers. The system consists of two major components: a PC application and a hardware component controlled by an FPGA device. The role of the system implemented in the FPGA device is to acquire and process data related to the DC motor's operation, to control the motor's voltage and to exchange data with the PC application. The PC application provides to the user an interface for visualizing information related to the motor's operation and for interacting with the system. It implements speed and position controllers based on PID algorithm and artificial neural networks, and provides multiple auto-tuning methods for automatic evaluation of the PID controllers parameters and also training sets for the neural network controller. The main advantage of the system is that it allows to automatically determine the control parameters for different DC motors without any prior knowledge regarding the motor parameters, and to easily verify the performances of the controllers.