Абстрактный

Simulation of DTC IM Based on PI& Artificial Neural Network Technique

Kusuma Gottapu ,YV Prashanth ,P Mahesh , Y Sumith , P.Shyam kiran

In this paper, we have introduced a whole new idea of the Artificial Neural Network technique used for flux position estimation & sector selection to reduce the torque & flux ripples. Direct Torque Control (DTC) of Induction Motor drive has quick torque response without complex orientation transformation and inner loop current control. The DTC has some drawbacks, such as the high torque & flux ripples, caused by sector changes. The important point in ANN based DTC is the right selection of the stator voltage vector. This project presents simple structured neural networks for flux position estimation and sector selection for induction motors. The Levenberg-Marquardt backpropagation technique has been used to train the neural network. The simple structure network facilitates a short training and processing times. The induction motor is non-linear system, the ANNs are excellent estimators in nonlinear systems.