Neural network-based shunt active filter with direct current control for power quality conditioning
by Nitin Gupta, S.P. Dubey, S.P. Singh
International Journal of Power Electronics (IJPELEC), Vol. 3, No. 6, 2011

Abstract: In this paper, a novel phase locked loop less control algorithm for harmonic and reactive power compensation with power factor improvement using three-phase shunt active power filter under non-ideal mains voltage conditions is presented. The performance of APF mainly depends upon how quickly and accurately compensation signal are estimated. The artificial neural network trained with conventional compensator data, can deliver compensation signals more accurately at varied load condition. The non-sinusoidal mains voltage problem is resolved by using neural network-based control system which estimates the reference compensation currents by extracting fundamental frequency components. The compensation process is based on sensing source currents only, without sensing source voltage and load currents, which gives more simplicity in control with less number of sensors. The proposed compensation approach has been first evaluated in MATLAB/Simulink. The simulated results are validated experimentally by developing a laboratory prototype using a floating-point DSP TMS320F28335 to show the effectiveness of the controller.

Online publication date: Sat, 31-Jan-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Power Electronics (IJPELEC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com