EPE Association: EPE 2003 - Topic 13c: Diagnostics

EPE 2003 - Topic 13c: Diagnostics
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2003 - Conference > EPE 2003 - Topic 13: SYSTEMS ENGINEERING > EPE 2003 - Topic 13c: Diagnostics

   [return to parent folder]

   Diagnostic start-up test to detect induction motor broken bars via short-time MUSIC algorithm applied to current space vector
By F. Cupertino; G. Martorana; L. Salvatore; S. Stasi [View]
[Download]

Abstract: This paper presents a new technique to diagnose broken rotor bars in squirrel cage induction machines. The technique is based on the analysis of the current space vector during motor starting via Short- Time MUSIC (STMUSIC) pseudo-spectrum. Differently from most of the diagnostic techniques already proposed in the technical literature, the approach presented in this work is effective regardless the load condition of the machine. Both STFFT and STMUSIC have been used to process the motor current space-vector. The latter approach, that is based on the eigen-analysis of the autocorrelation matrix, permits to keep only the principal frequency components of the signal and to decrease the noise influence, thus allowing a better interpretation of the current spectrum and an automatic fault detection procedure.

   Application of AI methods for rotor faults detection of the induction motor
By C.T.Kowalski; M.Pawlak [View]
[Download]

Abstract: The paper deals with rotor fault diagnosis problems of the induction motor using different Artificial Intelligence methods like: neural networks, fuzzy-logic and combined neuro-fuzzy methods. Rotor fault detectors based on these methods were developed. All detectors were trained and tested using measurement data of stator current spectra. The digital signal processor was used for practical realisation of AI-based fault detectors. All detectors were tested in off-line as well as on-line operation. The efficiency of developed neural detectors was evaluated.

EPE 2003 - Topic 13c: Diagnostics
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2003 - Conference > EPE 2003 - Topic 13: SYSTEMS ENGINEERING > EPE 2003 - Topic 13c: Diagnostics
	[return to parent folder]

	Diagnostic start-up test to detect induction motor broken bars via short-time MUSIC algorithm applied to current space vector By F. Cupertino; G. Martorana; L. Salvatore; S. Stasi	[View] [Download]
Abstract: This paper presents a new technique to diagnose broken rotor bars in squirrel cage induction machines. The technique is based on the analysis of the current space vector during motor starting via Short- Time MUSIC (STMUSIC) pseudo-spectrum. Differently from most of the diagnostic techniques already proposed in the technical literature, the approach presented in this work is effective regardless the load condition of the machine. Both STFFT and STMUSIC have been used to process the motor current space-vector. The latter approach, that is based on the eigen-analysis of the autocorrelation matrix, permits to keep only the principal frequency components of the signal and to decrease the noise influence, thus allowing a better interpretation of the current spectrum and an automatic fault detection procedure.

	Application of AI methods for rotor faults detection of the induction motor By C.T.Kowalski; M.Pawlak	[View] [Download]
Abstract: The paper deals with rotor fault diagnosis problems of the induction motor using different Artificial Intelligence methods like: neural networks, fuzzy-logic and combined neuro-fuzzy methods. Rotor fault detectors based on these methods were developed. All detectors were trained and tested using measurement data of stator current spectra. The digital signal processor was used for practical realisation of AI-based fault detectors. All detectors were tested in off-line as well as on-line operation. The efficiency of developed neural detectors was evaluated.