Estimation of the electromagnetic field radiating by electrostatic discharges using artificial neural networks

L. Ekonomou, G. P. Fotis, T. I. Maris, P. Liatsis

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


An artificial neural network (ANN) model and more specifically a feedforward multilayer network, which uses the powerful backpropagation learning rule, is addressed in order to estimate the electric and magnetic field radiating by electrostatic discharges (ESDs). Plenty of actual measurements, carried out in the High Voltage Laboratory of the National Technical University of Athens are used in training, validation and testing processes. The developed ANN can be a necessary tool for laboratories involved in ESD tests, either facing a lack of suitable measuring equipment or for laboratories which want to compare their own measurements. This is extremely useful for the laboratories involved in the ESD tests according to the current IEC Standard [International Standard IEC 61000-4-2: Electromagnetic Compatibility (EMC), Part 4: Testing and measurement techniques, Section 2: Electrostatic discharge immunity test, Basic EMC Publication, 1995.], since the forthcoming revised version of this Standard will almost certainly include measurements of the radiating electromagnetic field during the verification of the ESD generators. The authors believe that the proposed ANN will be extensively used, since the produced electromagnetic field radiating by electrostatic discharges, can be calculated very easily and accurately by simply measuring the discharge current.

Original languageBritish English
Pages (from-to)1089-1102
Number of pages14
JournalSimulation Modelling Practice and Theory
Issue number9
StatePublished - Oct 2007


  • Artificial neural networks (ANN)
  • Electromagnetic field
  • Electrostatic discharge (ESD)
  • IEC 61000-4-2
  • International standard


Dive into the research topics of 'Estimation of the electromagnetic field radiating by electrostatic discharges using artificial neural networks'. Together they form a unique fingerprint.

Cite this