Kostas J. Satsios

Combined fuzzy logic and genetic algorithm techniques-application to an electromagnetic field problem

The influence of a faulted electrical power transmission line on a buried pipeline is investigated. The induced electromagnetic field depends on several parameters, such as the position of the phase conductors, the currents flowing through conducting materials, and the earth resistivity. A fuzzy logic system was used to simulate the problem. It was trained using data derived from finite element method calculations for different configuration cases (training set) of the above electromagnetic field problem. After the training, the system was tested for several configuration cases, differing significantly from the training cases, with satisfactory results. It is shown that the proposed method is very time efficient and accurate in calculating electromagnetic fields compared to the time straining finite element method. In order to create the rule base for the fuzzy logic system a special incremental learning scheme is used during the training. The system is trained using genetic algorithms. Binary and real genetic encoding were implemented and compared.

Inductive interference caused to telecommunication cables by nearby AC electric traction lines. Measurements and FEM calculations

The paper investigates the inductive interference caused by AC electric traction lines to nearby buried telecommunication cables. Measurements according to the directives of the International Telecommunication Union (ITU) and calculations using the finite element method (FEM) are presented for a real system. This system consists of an AC electric traction line of the Greek Railways Organization and a buried cable of the Greek Telecommunications Organization. Finally, an analysis concerning the most important operational parameters in determining electric traction line influence is presented. Such parameters are the separation distance between the electric traction line and the buried telecommunication cable, the earth resistivity as well as the number and the material of the mitigation wires.

Finite element computation of field and eddy currents of a system consisting of a power transmission line above conductors buried in nonhomogeneous earth

The present work investigates the electromagnetic field and the eddy currents of a power system consisting of a faulted power transmission line above parallel conductors buried in nonhomogeneous earth. The electromagnetic field diffusion equation has been numerically solved, using the finite element method (FEM). Using FEM results, magnetic vector potential distribution in the cross-section of the parallel exposure, as well as eddy currents induced in all conductive parts, are calculated for various nonhomogeneous earth models. An analysis concerning the most important operational parameters in determining power transmission line influence is presented. Such parameters are the depth of the first earth layer, the resistivities of the different earth layers and the number of the mitigation wires.

The influence of nonhomogeneous earth on the inductive interference caused to telecommunication cables by nearby AC electric traction lines

This work investigates the inductive interference caused by AC electric traction lines to nearby buried telecommunication cables, in the presence of a nonhomogeneous earth. The two dimensional, quasi stationary electromagnetic field diffusion equation has been numerically solved by using the finite element method (FEM), in a system involving an AC electric traction line of the Greek Railways Organization and a buried cable of the Greek Telecommunications Organization. Using FEM results, magnetic vector potential in the cross-section of the examined system, as well as the longitudinal electromotive force induced in the circuit formed by the telecommunication cable and earth, are calculated. A rigorous parametric analysis concerning various nonhomogeneous earth models has shown a significant influence of the depth and resistivity of the first earth layer, as well as of the resistivities of the different earth layers, on the electromagnetic field and on the inductive interference caused to the buried telecommunication cable.

An artificial intelligence system for a complex electromagnetic field problem. I. Finite element calculations and fuzzy logic development

Artificial intelligence (AI) has been used to determine the electromagnetic field in the complex problem of a faulty overhead transmission line above earth and a buried pipeline. A suitable AI system for scaling finite element electromagnetic field calculations has been developed. This system was trained by using finite element calculations for configurations, i.e., cases having different distances between the overhead transmission line and the buried pipeline as well as different earth resistivities. The AI system may be used to calculate the electromagnetic field in new cases differing significantly from the cases used for training.

An artificial intelligence system for a complex electromagnetic field problem. II. Method implementation and performance analysis

For pt. I see ibid., vol. 35, no. 1, p. 516-22 (1999). An artificial intelligence system has been developed to determine the electromagnetic field in the complex problem of a faulty overhead transmission line above earth and a buried pipeline. The amplitude and phase of the magnetic vector potential (MVP) in the earth around the pipeline neighborhood, including the pipeline itself, are calculated, The performance of the trained fuzzy logic system (FLS) described in Part I was tested extensively for various configurations of the above electromagnetic field problem, differing significantly from the cases used for training. The trained FLS parameters required to calculate the electromagnetic field by simple formulas are also presented.

A fuzzy logic system for calculation of the interference of overhead transmission lines on buried pipelines

Abstract The influence of a faulted electrical power transmission line on a buried pipeline is investigated. A calculation tool is suggested. Finite element solutions of field equations are used combined with artificial intelligence methods. The electromagnetic field depends on several parameters, such as the position of the phase conductors, the currents flowing through the conducting materials and the resistivity of the earth. A fuzzy logic system was used to simulate the problem. It was trained using data derived from finite element method (FEM) calculations for different configuration cases (training set) of the above electromagnetic field problem. After the training, the system was tested for several configuration cases, differing significantly from the training cases with satisfactory results. It is shown that the proposed method is very time efficient and accurate in calculating the electromagnetic fields compared to the time straining finite element method. An important feature of the fuzzy logic system is that it consists of a varying rule base and is trained using genetic algorithms. In order to create the rule base for the fuzzy logic system a special operation is used at the beginning of the training. Afterwards, the training of the system is achieved with the use of a genetic algorithm (GA) that implements some special operators.

Fuzzy logic for scaling finite element solutions of electromagnetic fields

Artificial intelligence (AI) has been used to determine the quasi-stationary two-dimensional electromagnetic fields within rectangular boundaries. Amplitude and phase of magnetic vector potential have been calculated in an iron slot with an embedded current carrying conductor. A suitable fuzzy neural network (FNN) for scaling finite elements electromagnetic field calculations has been developed. FNN has been trained, using finite elements calculations within rectangular boundaries. Then, FNN has been used to calculate the field in a new geometry differing significantly from the geometries used for training. It was concluded that FNN may be used to scale results from one geometry to another with negligible errors.