INDUCTIVE COUPLING BETWEEN OVERHEAD POWER LINES AND NEARBY METALLIC PIPELINES. A NEURAL NETWORK APPROACH

• Main Authors: Levente CZUMBIL, Dan Doru MICU, DenisaȘTEȚ, Andrei CECLAN
• Format: Article
• Language: English
• Published: Technical University of Cluj-Napoca 2015-12-01
• Series: Carpathian Journal of Electrical Engineering
• Subjects: electromagnetic compatibility; electromagnetic interference; finite element methods; neural networks; pipelines; transmission lines
• Online Access: http://cee.cunbm.utcluj.ro/wp-content/uploads/2018/12/CJEE20153.pdf
• ISSN: 1843-7583; 1843-7583

The current paper presents an artificial intelligence based technique applied in the investigation of electromagnetic interference problems between high voltage power lines (HVPL) and nearby underground metallic pipelines (MP). An artificial neural network (NN) solution has been implemented by the authors to evaluate the inductive coupling between HVPL and MP for different constructive geometries of an electromagnetic interference problem considering a multi-layer soil structure. Obtained results are compared to solutions provided by a finite element method (FEM) based analysis and considered as reference. The advantage of the proposed method yields in a simplified computation model compared to FEM, and implicitly a lower computational time.