Neural Networks Applied to the Control of a Four-Wire Shunt Active Power Filter

Authors

  • Marcelo G. Villalva FEEC - UNICAMP CEP 13083 - 852 , Caixa Postal 6101 , Campinas - SP, Brasil
  • Ernesto Ruppert Filho FEEC - UNICAMP CEP 13083 - 852 , Caixa Postal 6101 , Campinas - SP, Brasil

DOI:

https://doi.org/10.18618/REP.2005.1.023030

Keywords:

Active Filter, adaline, neural network

Abstract

This paper presents a four-wire shunt active power filter fully controlled with neural networks. The paper is centered on a current compensation method based on adaptive linear elements (adalines), which are powerful and easy-to-use neural networks. The reader will find here an introduction about these networks, an explanatory section about the achievement of Fourier series with adalines, and the full description of an adaline-based selective current compensator. The paper also brings a discussion about the use of a feedforward neural network in the current controller of the active filter, as well as simulation and experimental results obtained with a prototype of a shunt active power filter.

Downloads

Download data is not yet available.

Author Biographies

Marcelo G. Villalva, FEEC - UNICAMP CEP 13083 - 852 , Caixa Postal 6101 , Campinas - SP, Brasil

graduated in electrical engineering at the University of Campinas (UNICAMP) in 2002. He received his master's degree and now pursues doctoral studies, both at UNICAMP.

Ernesto Ruppert Filho, FEEC - UNICAMP CEP 13083 - 852 , Caixa Postal 6101 , Campinas - SP, Brasil

graduated in electrical engineering at the University of Campinas (UNICAMP) and received his master's and his doctorate in 1971, 1974, and 1983 respectively. Since 1972 he has been with UNICAMP as a faculty member and as a researcher. His research interests include power electronics, superconductors, pwer systems, distributed generation, electric machines, and motor drives.

References

R. El Shatshat, M. Kazerani, and M. M. A. Salama, "Modular approach to active power-line harmonic filtering", in Proceedings of the 29th Annual IEEE Power Electronics Specialists Conference (PESC), vol. 1, pp. 223-228, 1998. https://doi.org/10.1109/PESC.1998.701903 DOI: https://doi.org/10.1109/PESC.1998.701903

M. Rukonuzzaman and M. Nakaoka, "Adaptive neural network based harmonic current compensation in active power filter", in Proceedings of the International Joint Conference on Neural Networks (IJCNN), vol. 3, pp. 2281-2286, 2001. https://doi.org/10.1109/IJCNN.2001.938522 DOI: https://doi.org/10.1109/IJCNN.2001.938522

J. R. Vazquez and P. Salmeron, "Active power filter control using neural network technologies", in IEE Proceedings - Electric Power Applications, vol. 150, no. 2, pp. 139-145, 2003. https://doi.org/10.1049/ip-epa:20030009 DOI: https://doi.org/10.1049/ip-epa:20030009

F. P. Marafão, P. Mattavelli, S. Buso and S. M. Deckmann, "Repetitive-based control for selective active filters using discrete cosine transform", Eletrônica de Potência, vol. 9, no. 1, pp. 29-36, 2004. https://doi.org/10.18618/REP.2004.1.029036 DOI: https://doi.org/10.18618/REP.2004.1.029036

P. Mattavelli and S. Fasolo, "A closed-loop selective harmonic compensation for active filters", in Proceedings of the 15th Annual IEEE Applied Power Electronics Conference and Exposition (APEC), vol. 1, pp. 399-405, 2000. https://doi.org/10.1109/APEC.2000.826134 DOI: https://doi.org/10.1109/APEC.2000.826134

S. Haykin, Neural Networks - A Comprehensive Foundation, Prentice Hall, 1998.

M. T. Hagan, H. B. Demuth and M. H. Beale, Neural Network Design, PWS Publishing Company, 1995.

B. Widrow and R. Winter, "Neural nets for adaptive filtering and adaptive pattern recognition", Computer, vol. 21, no. 3, pp. 25-39, 1988. https://doi.org/10.1109/2.29 DOI: https://doi.org/10.1109/2.29

B. Widrow and M. A. Lehr, "30 years of adaptive neural networks: perceptron, madaline, and backpropagation", in Proceedings of the IEEE, vol. 78, no. 9, pp. 1415-1442, 1990. https://doi.org/10.1109/5.58323 DOI: https://doi.org/10.1109/5.58323

M. G. Villalva, E. Ruppert F., "Current controller with artificial neural network for 3-phase 4-wire active filter", in Proceedings of the 35th Annual IEEE Power Electronics Specialists Conference (PESC), vol. 2, pp. 993-998, 2004. https://doi.org/10.1109/PESC.2004.1355556 DOI: https://doi.org/10.1109/PESC.2004.1355556

M. G. Villalva, E. Ruppert F., "Current controller with 3-D SVPWM for 3-phase 4-wire active filters", IASME Transactions, vol. 1, no. 2, pp. 259-264, 2004.

F. P. Marafão, S. M. Deckmann, J. A. Pomilio and R. Q. Machado, "A software-based PLL model: analysis and applications", in XV Congresso Brasileiro de Automática (CBA), 2004.

Downloads

Published

2005-06-30

How to Cite

[1]
M. G. Villalva and E. R. Filho, “Neural Networks Applied to the Control of a Four-Wire Shunt Active Power Filter ”, Eletrônica de Potência, vol. 10, no. 1, pp. 23–30, Jun. 2005.

Issue

Section

Original Papers