The aim of this work is to improve the tracking performance of separately excited DC motor by exploring the features of Artificial Neural Network (ANN). The neural network controller enhances the performance and dynamics of the DC motor in comparison to conventional Proportional Integral (PI) controller. The simulations are carried out with MATLAB simulink. The ANN-based PMDC drive is suitable for a vast number of industries like paper mills, textile mills, etc.

The DC motors have staged a comeback with the advent of the silicon controlled rectifiers used for power conversion, facilitating a wide range of speed control of these motors. The permanent magnet DC motor with Proportional Integral (PI) controller is widely used in industries where the load changes are very small. However, in certain applications like rolling mill or machine tools where the system parameters vary substantially, the conventional controllers like PI or Proportional Integral Derivative (PID) are not preferable due to the fact that the drive operates under the wide range of changing load characteristics. The modern automated industries introduces the variable speed drives, increase the productivity and thereby increases the efficiency considerably by 15-27%. Since the conventional controllers are delivering poor performance for the variable speed drive, it is necessary to have an efficient controller which suits nonlinear operating condition.

The Artificial Neural Network (ANN), often called Neural Network, is the most generic form of artificial intelligence for emulating the human thinking process compared to the rule-based expert system and the fuzzy logic system. The proposed scheme presents the ANN application in estimating and controlling the speed of the PMDC drive to a set value.

The starting performance of the separately excited DC motor is affected by its nonlinear behavior. The speed control DC motor is done with different control strategies. DC motors are widely used in industrial and domestic equipment. The control of the position of a motor with high accuracy is required. A desired speed may be tracked when a desired shaft position is also required. In fact, a single controller may be required to control both the position and the speed. The reference signal determines the desired position and/or speed. The controller is selected so that the error between the system output and reference signal eventually tends to its minimum value, ideally zero. There are various types of DC motor. Depending on the type, a DC motor may be controlled by varying the input voltage, whilst another motor can be controlled only by changing the current input.

Electrical and Electronics Engineering Journal, ANN Controller-Fed PMDC Drive, Artificial Neural Network, Artificial Intelligence, Complicated Technological Systems, DC Motor Parameters, Electro-Mechanic Systems, Neural Network Processing Elements, Intercommunication Protocols.