Real-time frequency and harmonic evaluation using artificial neural networks

Abstract

With increasing harmonic pollution in the power system, real-time monitoring and analysis of harmonic variations have become important. Because of limitations associated with conventional algorithms, particularly under supply-frequency drift and transient situations, a new approach based on non-linear leastsquares parameter estimation has been proposed as an alternative solution for high-accuracy evaluation. However, the computational demand of the algorithm is very high and it is more appropriate to use Hopfield type feedback neural networks for real-time harmonic evaluation. The proposed neural network implementation determines simultaneously the supply-frequency variation, the fundamental-amplitude/phase variation as well as the harmonics-amplitude/phase variation. The distinctive feature is that the supply-frequency variation is handled separately from the amplitude/phase variations, thus ensuring high computational speed and high convergence rate. Examples by computer simulation are used to demonstrate the effectiveness of the implementation. A set of data taken on site was used as a real application of the system.

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

“…However, computational complexities such as matrix inversion involved in KF make it less appealing for real-time hardware implementation. The recursive nature of ANN based techniques proposed in the literature [8][9][10][11], results in a much slower response time (e.g. 35 ms [11]).…”

“…However, the computational complexity of these methods is much more than that of the FFT whilst the time taken for harmonic extraction is similar. The use of ANNs for real-time harmonic monitoring has been the focus of many researchers [8][9][10][11]. ANNs provide simple and straightforward techniques for selectively tracking individual harmonic components.…”

A new scheme for power factor correction and active filtering for six-pulse converters loads

“…The schemes presented in Reference [17] makes it possible to perform any real-world task described by a certain Boolean function via an SLP or a dynamic neuron. For a few years, ANN techniques have been widely explored for signal decomposition in electrical systems and are very promising in the field, as discussed in References [18][19][20][21][22][23]. Indeed, the learning capacities of the ANNs allow an online adaptation to every changing parameter of the electrical system, e.g., nonlinear and time-varying loads.…”

“…In this Subsection, the mathematical formulation of adaptive linear neural network (ADALINE) [18][19][20][21][22][23] is outlined as follows. Consider an arbitrary signalY (t) with Fourier series expansion as…”

“…The proportional-integral (PI) controllers are implemented in daxis and q-axis based on the decoupled state-space equations of the T-type active power filter. The load side dynamics are incorporated in the feed-forward control loop by using two groups of synchronous frame adaptive linear neural networks (SADALINEs) [13][14][15][16][17][18][19][20][21][22][23] in d-axis and q-axis, respectively, for fast estimation of the fundamental components of nonlinear load currents. Besides, a separate proportional-integral (PI) controller is adopted in the outer voltage loop for balancing the active power flow of the voltage source inverter.…”