Artificial Neural Network Based Direct Torque Control for Variable Speed Wind Turbine Driven Induction Generator

This paper presents an artificial neural network (ANN) based direct torque control (DTC) scheme to control speed and torque of IG drive over a wide speed range without using PWM controller. With the induction machine stator and rotor flux parameters, speed of IG is predicted by using ANNSP scheme. In wind turbine driven IG set, if wind speed alters, output torque of IG varies, results in variation of output voltage and electric power. In other circumstances, there may be requirement to change the IG speed, which has to be achieved more rapidly. Robust technique to reach the desired states in a stable manner is necessary for such a system. Hence this paper aims to present a technique to control speed and torque with very diminutive time delay compared to preceding techniques. Simulation results shows that the proposed prediction method effectively diminishes the torque and flux ripples under variable speed circumstances. The system is studied using MATLAB/SIMULINK, shows that ANN speed recognition optimization algorithm has better tracking capability and fitness, as well as favorable static and dynamic properties. The outputs of ANN mechanism is compared with that of PI controller and the results demonstrate the influence of ANN is enhanced and fast compared to PI. The system is also verified and proved to be operated stably with very low speed, sudden speed reversals, at low torque and at high torque.