By Topic

A Predictive Current Regulator Using Linear Neural Networks For Three-phase Voltage Source PWM-Inverter

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Guang-Da Chen ; Sch. of Power & Mech. Eng., Wuhan Univ. ; Yi-Zhou Shen ; Mian-Hua Huang

This paper presents a predictive control strategy based on linear neural networks for the current control of a three-phase voltage source PWM-inverter. The base of this regulator is a conventional deadbeat control loop which ensures the relatively good dynamic performance of system. However, because of the inherent characteristic of deadbeat control, existing time delay between system reference input and actual output, therefore causes the steady state error when the input is sinusoidal. To eliminate this error, a novel predictive control method is presented in this paper. Based on the deadbeat controller, two sinusoidal predictors implemented by linear neural networks are further introduced for the predictions of reference current and the AC side voltage respectively. As a result, the time delay and steady state error are minimized to almost zero. Simulation results are presented to verify the effectiveness of the proposed algorithm

Published in:

Neural Networks and Brain, 2005. ICNN&B '05. International Conference on  (Volume:2 )

Date of Conference:

13-15 Oct. 2005