期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2013
卷号：5
期号：4
DOI：10.15676/ijeei.2013.5.4.4
出版社：School of Electrical Engineering and Informatics
摘要：The power quality enhancement is very mandatory with the newer generationload equipments, whose performance is very sensitive to power quality disturbancesespecially with voltage sag, Harmonics and Interruption. The power electronic basedpower conditioning devices can be the effective solution to enhance the quality of thepower supplied to the power distribution system. The series connected DynamicVoltage Restorer (DVR) is one of the effective solution to mitigate power qualityproblems in the distribution system. In this paper, the Artificial Neural Network (ANN)controlled DVR is designed and the performance of the rectifier load connected systemis investigated with conventional Proportional-Integral (PI) controller. The Levenberg-Marquardt (LV) Back propagation algorithm is used to implement the control scheme ofthe Voltage Source Inverter (VSI). The ANN is trained offline using data from PIcontroller. In addition to the compensation of voltage sag and harmonics, the DVR isalso used to protect a linear load from various disturbances in the source voltage. Threedifferent types of faults with two level of voltage sag are analyzed and the performanceof DVR with these disturbances is modeled using MATLAB/SIMULINK. Thecomprehensive result of the PI and ANN controllers are also presented
关键词：Artificial Neural Network (ANN); Custom Power Devices (CPDs); Dynamic Voltage;Restorer (DVR); Proportional-Integral (PI);Power Distribution system; Power Quality;(PQ).
