Synchronous Reference Frame Based Active Filter Current Reference Generation Using Neural Networks

The increased use of nonlinear devices in industry has resulted in direct increase of harmonic distortion in the industrial power system in recent years. The significant harmonics are almost always 5th, 7th, 11th and the 13th with the 5th harmonic being the largest in most instances. Active filter systems have been proposed to mitigate harmonic currents of the industrial loads. The most important requirement for any active filter is the precise detection of the individual harmonic component's amplitude and phase. Fourier transform based techniques provide an excellent method for individual harmonic isolation, but it requires a minimum of two cycles of data for the analysis, does not perform well in the presence of subharmonics which are not integral multiples of the fundamental frequency and most importantly introduces phase shifts. To overcome these difficulties, this paper proposes a multilayer perceptron neural network trained with back-propagation training algorithm to identify the harmonic characteristics of the nonlinear load. The operation principle of the synchronous-reference-frame-based harmonic isolation is discussed. This proposed method is applied to a thyristor controlled DC drive to obtain the accurate amplitude and phase of the dominant harmonics. This technique can be integrated with any active filter control algorithm for reference generation

[1]  Tung-Sang Ng,et al.  Gradient-based adaptive IIR notch filtering for frequency estimation , 1990, IEEE Trans. Acoust. Speech Signal Process..

[2]  P. Salmeron,et al.  Practical design of a three-phase active power-line conditioner controlled by artificial neural networks , 2005, IEEE Transactions on Power Delivery.

[3]  Po-Tai Cheng,et al.  Experimental verification of dominant harmonic active filter (DHAF) for high power applications , 1998, Conference Record of 1998 IEEE Industry Applications Conference. Thirty-Third IAS Annual Meeting (Cat. No.98CH36242).

[4]  R.G. Harley,et al.  Neural Network Based Method for Predicting Nonlinear Load Harmonics , 2007, IEEE Transactions on Power Electronics.

[5]  Ned Mohan,et al.  Hybrid-active filtering of harmonic currents in power systems , 1995 .

[6]  M. F. McGranaghan,et al.  Designing harmonic filters for adjustable speed drives to comply with IEEE-519 harmonic limits , 1997, 1997 Rural Electric Power Conference (Cat. No.97CH36079).

[7]  T.A. George,et al.  Harmonic power flow determination using the fast fourier transform , 1991, IEEE Power Engineering Review.

[8]  H. Akagi,et al.  A practical approach to harmonic compensation in power systems-series connection of passive and active filters , 1990, Conference Record of the 1990 IEEE Industry Applications Society Annual Meeting.

[9]  B. Burton,et al.  Reducing the computational demands of continually online trained artificial neural networks for system identification and control of fast processes , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[10]  Subhashish Bhattacharya,et al.  Active filter solutions for utility interface of industrial loads , 1996, Proceedings of International Conference on Power Electronics, Drives and Energy Systems for Industrial Growth.