Fani E. Asimakopoulou

Applying genetic algorithms for the determination of the parameters of the electrostatic discharge current equation

The aim of this paper is the estimation of the parameters of possible equations, which describe the current during an electrostatic discharge using genetic algorithms. Aberrations between simulations and the waveform described in the standard render necessary the development of an equation that will describe the discharge current. The input data of the genetic algorithm are real current measurements produced by an electrostatic discharge generator. By using these data, the genetic algorithm is a means to find optimized parameters of the mathematical equations. The satisfactory agreement between the experimental and optimized data proves the efficiency of the genetic algorithm.

Estimation of ground enhancing compound performance using Artificial Neural Network

Grounding system constitutes an essential part of the protection system of electrical installations and power systems against lightning and fault currents. Therefore, it is of paramount importance that engineers ensure as low values for grounding resistance as possible, during the designing phase as well as the lifecycle of the grounding system. A widely used technique of reducing the grounding resistance value, in case of high soil resistivity values, or lack of adequate space for the installation of grounding systems, is the use of ground enhancing compounds. This paper presents a methodology, for the evaluation of grounding resistance, under various meteorological conditions, of grounding systems embedded in natural soil as well as in ground enhancing compounds, using Artificial Neural Network (ANN). The ANN training is based on field measurements that have been performed in Greece during the last year. As a matter of fact, this is a first step to develop a new method for estimating variations of grounding resistance value.

Artificial neural network approach on the seasonal variation of soil resistance

Objective of this paper is the development of a methodological approach for estimating the ground resistance by using artificial intelligence techniques (specifically, Artificial Neural Network). The value of the ground resistance greatly depends on the grounding system and the properties of the soil, where the system is embedded. Given that the value of soil resistivity fluctuates during the year, the ground resistance does not have one single value. The approach proposed in this paper, takes advantage of the capability of artificial neural networks (ANNs) to recognize linear and non-linear relationships between various parameters. By taking into account measurements of resistivity and rainfall data accrued for previous days, the ground resistance is estimated. On that purpose ANNs have been trained and validated by using experimental data in order to examine their ability to predict the ground resistance. The results prove the effectiveness of the proposed methodology.

Comparison of circuit models for the simulation of soil ionization

The main characteristic of the transient behaviour of a grounding system is the decrease of the soil resistivity and consequently of the grounding impedance, due to soil ionization phenomena that take place, when the density of the injected current exceeds a critical value. In this paper two circuit models proposed by researchers have been implemented using the ATP/EMTP programme in order to simulate the transient response of a grounding system taking soil ionization into account. The simulation results are compared to measurements received by imposing impulse voltages on soil samples. The accuracy of each model is evaluated according to the level of proximity to the oscillogramms and conclusions are drawn about the effectiveness of each modeling approach.

Estimation of the Earth Resistance by Artificial Neural Network Model

The aim of this paper is to investigate the estimation of the variation of ground resistance throughout the year by using artificial neural networks (ANNs). An ANN was trained, validated, and tested with different training algorithms by using experimental data of soil resistivity, ground resistance, and rainfall in order to select the optimum training algorithm and the respective parameters and predict the behavior of the ground resistance of a single rod. Moreover, a sensitivity analysis of the proposed ANN was carried out in order to determine the impact of certain factors on the efficiency of the ANN. The high value of the correlation index between estimated and experimental values demonstrates the high efficiency of the ANN. The proposed methodology based on ANN is a useful tool for the estimation of the grounding resistance during the year in case of difficulties in measuring its value.

Uncertainty of Soil Breakdown Voltage

Aim of this work is the analysis of the components of uncertainty and the estimation of the uncertainty regarding the determination of the breakdown voltage associated with the soil critical electric field. For that reason, series of measurements have been conducted by inducing impulse voltages to soil samples with different moisture content in order to determine the impact of the moisture content on the uncertainty of the breakdown voltage.

Parameter evaluation of the equation of the electrostatic discharge current using genetic algorithms as optimization tool

The scope of this paper is the parameter evaluation of equations that possibly can describe the current during an electrostatic discharge, using genetic algorithms. It is necessary to find an equation for the electrostatic discharge current, because there are aberrations among simulations and the waveform described in the IEC 61000-4-2 standard. In this work the genetic algorithm has been applied on the parameters of four equations. The genetic algorithm has as input data real measurements of the discharge current produced by an electrostatic discharge generator and, using these data, optimizes the parameters of the mathematical equations. The comparison between the experimental and the optimized data proves the efficiency of the genetic algorithm and the most suitable equation among the four for the discharge current derives