Possibilities of the recognition of electromechanical devices by their noise characteristics

Gražulevičius, Gediminas; Gražulevičius, Algirdas

Use this url to cite publication: https://hdl.handle.net/20.500.14911/142724

Possibilities of the recognition of electromechanical devices by their noise characteristics

Details

Publication Type (CRIS)

Straipsnis recenzuojamoje užsienio tarptautinės konferencijos medžiagoje / Article in peer-reviewed foreign international conference proceedings (P1d)

Publication Type (eLABa)

Straipsnis recenzuotame konferencijos darbų leidinyje / Article published in peer-reviewed conference proceedings (P1d)

Author(s)

Author	Affiliation
Gražulevičius, Gediminas	Kompiuterijos ir ryšių technologijų katedra / Department of Computer Science and Communications Technologies (0559)
Gražulevičius, Algirdas	Kompiuterijos ir ryšių technologijų katedra / Department of Computer Science and Communications Technologies (0559)

Title

Possibilities of the recognition of electromechanical devices by their noise characteristics

[en]

G. Gražulevičius, A. Gražulevičius

Is part of

Proceedings of the 6th International Conference ELEKTRO 2006: Žilina, Slovak Republik, May 23-24, 2006 / University of Žilina

Published In

Year	Start Page	End Page
2006	22	24

Publisher

Žilina : Žilina University publishers, 2006

Extent

p. 22-24

URI

URI
https://hdl.handle.net/20.500.14911/142724

Cited references

Science / Art Area

Technologijos mokslai / Technological sciences (T)

Field of Science / Art

Elektros ir elektronikos inžinerija / Electrical and electronic engineering (T001)

Abstract (en)

A possibility of recognizing mechanical, electromechanical and other devices by the chacteristics of noise induced by them is considered. The recognition algorithm can aply two criteria - differences in noise spectrum and noise levels. The devices are recognized by the minimum of these differences. The reliability of both recognition algorithms was tested by trying to recognize one of four identical electromechanical devices. The experiment has shown the recognition reliability to be not less than 96%. It has been determined that the algorithm of recognition by the noise level has a lower dispersion of the recognition criterion in comparison with algorithm of recognition by the noise spectrum.