Using artificial neural network to analyze harmonic overvoltages during power system restoration

Abstract

SUMMARYDuring early stage of primary restoration process, unexpected overvoltage may happen due to nonlinear interaction between the unloaded transformer and the transmission system. Such an overvoltage might damage some equipment and delay power system restoration. Artificial neural network (ANN) is addressed in this work, in order to estimate the temporary overvoltages (TOVs) due to transformer energization. In the proposed methodology, Levenberg-Marquardt second order method is used to train the multilayer perceptron. Equivalent parameters of the network are added to ANN inputs to achieve good generalization capability for trained ANN. The developed ANN is trained with the worst case scenario of switching angle and remanent flux, and tested for typical cases. The simulated results for a partial of 39-bus New England test system, show that the proposed technique can estimate the peak values and duration of switching overvoltages with good accuracy.

Investigation of Transmission Line Models for Switching Overvoltages Studies

“…This leads to a higher level of saturation, resulting in higher harmonic components of the inrush current that again results in increased voltages. Transformer saturation is result of overvoltage and cause core heating and copious harmonic current generation [4,14]. In this work for investigating TL models, several case studies have been chosen that are portions of 39-bus New England test system and their parameters are listed in [19].…”

“…one π section for every 25 km. Also, in [14], TLs are simulated by distributed model for switching overvoltages study. Results of this comparison are presented in Section 7.…”

The Study of Switching Overvoltages under Power System Restoration Scenario Using Extended Delta-Bar-Delta Algorithm

“…Transient overvoltages are a consequence of switching operations on long transmission lines, or the switching of capacitive devices, and may result in arrester failures. Ferro-resonance is a nonharmonic resonance characterized by overvoltages whose waveforms are highly distorted and can cause catastrophic equipment damages [1,[5][6][7][8].…”

Acceleration Harmonics Identification for an Electro-Hydraulic Servo Shaking Table based on a Nonlinear Adaptive Algorithm

“…Cao et al [4] proposed a new method based on Radial basis function (RBF) neural network to detect each order harmonic's amplitude and phase of a distorted harmonic signal. Ketabi et al [5] introduced a multilayer feedforward neural network to analyze harmonic overvoltage during power system restoration. The effect and precision performance of this scheme had been proved to be satisfied by experimental results.…”