DocumentCode
1823117
Title
Accurate methods for solving electromagnetic interference problems between power lines and underground metallic pipelines
Author
Micu, Dan Doru ; Czumbil, Levente ; Ceclan, Andrei ; Darabant, Laura
Author_Institution
Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania
fYear
2009
fDate
1-4 Sept. 2009
Firstpage
1
Lastpage
5
Abstract
The accurate calculation of the current densities induced in soil by HV transmission lines in normal and fault conditions is one of the most important steps for the study of the electromagnetic interference between transmission lines and underground metallic structures (i.e. metallic gas pipelines). New analytical formulas for the induced current densities in the two-layer soil case are derived. In the second part of the paper, the author´s contribution relates to the exposure and implementation in an original approach of a robust neural network for the study of electromagnetic interferences between high voltage power lines and metallic underground pipelines, for complex constructive geometries. The results obtained with neural networks are compared to the finite element solutions considered as standard ones. Our contribution relates to the implementation of the neural network AI technique, to the study of electromagnetic interference problems and the testing of the neural networks used in the studied case.
Keywords
current density; electric conduits; electromagnetic interference; finite element analysis; neural nets; pipelines; power engineering computing; power transmission lines; soil; underground cables; HV transmission lines; electromagnetic interference problems; finite element solution; induced current density; power lines; robust neural network; two-layer soil case; underground metallic pipelines; Current density; Electromagnetic interference; Finite element methods; Geometry; Neural networks; Pipelines; Power transmission lines; Robustness; Soil; Voltage; Electromagnetic interference; High voltage power lines; Induced current densities; Metallic pipelines; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Universities Power Engineering Conference (UPEC), 2009 Proceedings of the 44th International
Conference_Location
Glasgow
Print_ISBN
978-1-4244-6823-2
Type
conf
Filename
5429568
Link To Document