Recurrent-neural-network-based implementation of a programmable cascaded low-pass filter used in stator flux synthesis of vector-controlled inductionmotor drive

The concept of programmable cascaded low-pass filter for stator flux vector synthesis by ideal integration of stator voltages at any frequency was int roduced by Bose and Patel, A new form of implementation of this filter is b eing proposed here that uses a combination of recurrent neural network trai ned by Kalman filter and a polynomial neural network. The proposed structur e is simple, permits faster implementation by digital signal processor, and gives improved performance.