Abstract
The concept of programmable cascaded low-pass filter for stator flux vector synthesis by ideal integration of stator voltages at any frequency was introduced by Bose and Patel. A new form of implementation of this filter is being proposed here that uses a combination of recurrent neural network trained by Kalman filter and a polynomial neural network. The proposed structure is simple, permits faster implementation by digital signal processor, and gives improved performance.
Original language | English |
---|---|
Pages (from-to) | 662-665 |
Number of pages | 4 |
Journal | IEEE Transactions on Industrial Electronics |
Volume | 46 |
Issue number | 3 |
DOIs | |
State | Published - 1999 |
Externally published | Yes |