Abstract
The non-linear loads are increasing day by day. In many applications, the power electronic converters are used which are non-linear loads (NLLs). These loads drawn on-sinusoidal current waveform. The active harmonic power filters are employed to mitigate these harmonics. The accuracy of Harmonic Current Estimation (HCE) assumes importance for the good performance of active harmonics power filter. The conventional method namely Fourier series method is used to compute harmonic current. This method is computationally rigorous on real-time implementation. In this paper, an alternate approach namely Artificial Neural Network (ANN) approach is proposed to compute harmonic current. The feedforward with single hidden layer, feedforward architecture with multiple hidden layers, and cascaded neural architecture is investigated for harmonic current estimation. The architectures are compared in terms of accuracy and mathematical complexity. The suitable architecture for HCE is identified and results obtained are presented.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
