Low-cost embedded system for the IM fault detection using neural networks

Author

Pawlak, M. ; Kowalski, C.T.

Author_Institution

Inst. of Electr. Machines, Wroclaw Univ. of Technol., Wroclaw, Poland

fYear

2010

fDate

6-8 Sept. 2010

Firstpage

1

Lastpage

5

Abstract

This paper presents a realization of a low-cost, portable measurement system for induction motor fault diagnosis. The system is composed of a four-channel data acquisition recorder and laptop computer with specialized software. The diagnostic software takes advantage of the motor current signature analysis method (MCSA) for detection of rotor faults, voltage unbalance and mechanical misalignment. For diagnostics purposes the neural network technique is applied.

Keywords

computerised monitoring; data acquisition; embedded systems; fault diagnosis; induction motors; neural nets; power engineering computing; data acquisition recorder; induction motor fault detection; laptop computer; low cost embedded system; mechanical misalignment; motor current signature analysis method; neural networks; portable measurement system; voltage unbalance; Artificial neural networks; Fault detection; Induction motors; Rotors; Software; Stator windings; artificial neural networks; diagnostic; induction motor; stator current spectral analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Machines (ICEM), 2010 XIX International Conference on

Conference_Location

Rome

Print_ISBN

978-1-4244-4174-7

Electronic_ISBN

978-1-4244-4175-4

Type

conf

DOI

10.1109/ICELMACH.2010.5607947

Filename

5607947