DC motor requires a rotor speed sensor for accurate speed control. The speed sensors such as resolvers and encoders are used as speed detectors, but they increase cost and size of the motor and restrict the industrial drive applications.
So in these days, many papers have reported on the sensorless operation of DC motor.
This paper presents a new sensorless speed control strategy using neural net- works.
In classical control systems, knowledge on the controlled system is required in the form of a set of algebraic and differential equation, which analytically relate inputs and outputs. However, these models are often complex, rely on many assumptions, may contain parameters which are difficult to measure or may change significantly during operation and sometimes such mathematical models cannot be determined. Furthermore, classical control theory suffers from some limitations due to the nature of the controlled system. These problems can be overcome by using artificial intelligence-based control techniques, and these techniques can be used even when the analytical models are not known, and they can be less sensitive to parameter variation than classical control systems.
The most commonly used neural networks are feedforward multilayer types. Multilayer has three layers which are input layer, hidden layer and output layer. The optimal neural network structure was tracked down by trial and error, and it was found that 4-16-1 neural network gave correct results for the instantaneous rotor speed.
Also, learning method is very important in neural network. Supervised learning methods are typically used to train the neural network for learn the input/output pattern presented. The back-propagation technique adjusts the neural network weights during training.
The rotor speed is gained by weights and four inputs to the neural network, that is, armature voltages and currents. The satisfactory results have been found through the experiment in both the independency on machine parameters and the insensitivity to the load condition.