Three Phase Series Active Power Filter Based Adaptive Linear Neuron (ADALINE) to overcome voltage harmonics in power systems

Marselin Jamlaay

doi:10.46729/ijstm.v5i1.1054

Marselin Jamlaay Politeknik Negeri Ambon

DOI: https://doi.org/10.46729/ijstm.v5i1.1054

Keywords: Series Active Power Filter, Harmonics, Artificial Neural Networks

Abstract

Voltage harmonics in the power system can interfere with the work of equipment and reduce the quality of electrical power. This is overcome by using a Series Active Power Filter which is a three-phase Voltage Source Inverter (VSI). The artificial neural network compensation method is used as the control circuit of the Series Active Power Filter to generate a reference voltage from the harmonic distorted and unbalanced source voltage. The artificial neural network determines the amplitude of the sine and cosine components of the reference voltage. Computer simulation results show that the three-phase Series Active Power Filter with artificial neural network compensation method is effectively able to remove harmonics and produce a sinusoidal and balanced three-phase voltage that will be received by the load..

Downloads

Download data is not yet available.

References

[1] C. Sankaran, Power quality, CRC Press, 2002.
[2] H. Kawahira, T. Nakamura, S. Nakazawa, and M. Nomura, Active power ﬁlters, in Proc. JIEE-IPEC, Mar. 1983, pp. 981–992.
[3] Peng F. Z, Harmonic sources and filtering approaches, Industry Applications Magazine, IEEE, 2001 7(4): p.18-25.
[4] Green, T.C. and J.H, Marks, Control techniques for active power filters, Electric Power applications, IEEE Proceedings, 2005, 152(2):pp.369-381.
[5] Temurtas, F., et al., Harmonic detection using feed forward and recurrent neural networks for active filte, Electric Power Systems Research, 2004, 72(1): pp. 33-40.
[6] Hanny H. Tumbelaka, Thiang, Sorati, Aplikasi Jaringan Saraf Tiruan pada Shunt Active Power Filter Tiga Fasa, Proceeding of the 11th Industrial Electronics Seminar 2009, ITS, Surabaya.