The aim of the paper is to design a parallel distributed hysterisis band PWM current controller for a three level voltage source inverter (VSI) through an artificial neural network (ANN) approach. The ANN approach has been selected for this, since it has the potential to provide an improved method of deriving non-linear models which is complementary to conventional techniques. To illustrate the validity of this approach, an indirect vector controlled induction motor (IVCIM) drive has been considered as its application.For designing this, a feed forward neural network using the error back propagation training algorithm is selected. This network is trained so that it learns the nonlinear behavior of the conventional HBPWM controller. Thus the neural network acquires the features of an HBPWM controller and behaves as an PDHBPWM. The simulation model of an IVCIM drive employing PDHBPWM current controller is developed in SIMULINK/MATLAB environment. The performance of the proposed method is compared with conventional HBPWM current control scheme. From the observations made it is concluded that PDBPWM current controller is more efficient in terms of fault tolerance, switching loss and total harmonic distortion thus improving the performance of the drive.

Terms:VSI (Voltage Source Inverter), Vector Control,Hystersis Band Control,Parallel Distribution, Artificial Neural Network.