Pemulihan Tegangan Kedip Menggunakan Dynamic Voltage Restorer (DVR) dengan Kendali Constructive Levenberg Marquardt Neural Network

  • Dedy Kurnia Setiawan Universitas Jember

Abstract

Abstract

In this paper proposed an algorithm to control dynamic voltage
restorer (DVR). The proposed controller is using an artificial
neural network with Levenberg Marquardt method Constructive
Neural Network (CLMNN). The purpose of this control is to obtain
a DVR with a quick and accurate response while improving the
quality of the voltage due to the voltage flicker in low-voltage
systems. CLMNN use that is based on the configuration of hidden
layer neural network used can be changed to obtain the optimal
value. CLMNN used in the detection of the change in voltage
conditions, either in the form of fluctuations in the voltage
amplitude and phase changes in load. Once detected, CLMNN
generate a PWM signal as a control. To determine the performance
CLMNN controller, then the simulation is used as a comparison of
conventional controllers. Based on the simulation results it is
known that overshoot voltage of sensitive load decreased by 20%
when using CLMNN. In addition, the DVR is more stable with a
faster settling time, ie less than 0.01 seconds, whereas when using a
PI controller reaches 0.02 seconds.

Keywords— Dynamic Voltage Restorer (DVR), voltage flicker,
Levenberg Marquardt Constructive Neural Network

 

Published
2015-05-02
How to Cite
SETIAWAN, Dedy Kurnia. Pemulihan Tegangan Kedip Menggunakan Dynamic Voltage Restorer (DVR) dengan Kendali Constructive Levenberg Marquardt Neural Network. Jurnal Arus Elektro Indonesia, [S.l.], v. 1, n. 1, may 2015. ISSN 2443-2318. Available at: <https://jurnal.unej.ac.id/index.php/E-JAEI/article/view/1454>. Date accessed: 29 mar. 2024.
Section
Articles