A digital current controller for a PWM inverter using a neural network and its stability

Abstract
A digital current controller for a PWM (pulse width modulation) inverter using a neural network is presented. The current controller automatically tunes its gains to the optimal ones and compensates delay necessary for calculation of the controller itself, and it has a high performance in response to current control. The stability condition for the learning rate of the neural network is analyzed. The stable region of deviation of the load impedance is obtained by simulation.> Author(s) Ito, Y. Dept. of Electron. Mech. Eng., Nagoya Univ., Japan Furuhashi, T. ; Okuma, S. ; Uchikawa, Y.

This publication has 2 references indexed in Scilit: