Fast non-recursive extraction of individual harmonics using artificial neural networks

Abstract

Non-linear loads, which cause harmonic distortion, are increasingly being used in electrical power systems. This is causing a major concern and real-time harmonic

Virtual Instrument of Harmonics Detection Based on Neural Network Adaptive Filters

“…Furthermore, it proves that the weights of each subcircuit adaptive filter optimally approximate the peak values of the sine or cosine signals that correspond to the subcircuit in the noise interference current i(t) [9]- [10]. Therefore, the power harmonics can be detected using the output ( ) z t of the system or the weight of each sub circuit of the artificial neuron based on the real situation [11].…”

Effects of frequency deviation on the accuracy of harmonic analysis and mitigation

“…The paper presents a comparison of the effects of frequency deviation on the accuracy of extraction of signal harmonic components, for a number of widely used techniques used for PQ analysis including the above mentioned FT, Short Time FT (STFT), CWT, and the WPT variant of the DWT techniques together with an approach using artificial neural networks [6]. A study of the literature shows that such a comparison has not been published.…”

A Predictive Control Strategy for Mitigation of Commutation Failure in LCC-Based HVDC Systems

“…Reference [11] presents a control strategy which reduces the firing angle of valves once the commutating voltage is distorted. In this approach, the commutating voltage distortion is detected by extraction of its harmonic components, but according to [12], the time required to extract the harmonic components of a signal depends on its fundamental frequency which takes 20 ms in a 50 Hz system. Therefore, the proposed approach can only be effective in preventing repetitive commutation failures.…”