Wavelet transform and neural network techniques for inter-turn short circuit diagnosis and location in induction motor

Bessam, B.; Menacer, Arezki; Boumehraz, Mohamed; Cherif, Hakima

doi:10.1007/s13198-015-0400-4

Cited by 38 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…based on electrical monitoring such as stator current monitoring [6], axial flux, instantaneous power [7], active reactive power, air-gap torque monitoring and current Park components [8] followed by thermal and vibration monitoring [9]. Several authors applied modern computing approaches such as genetic algorithm, wavelet analysis, expert systems, Neural Networks [10,11], and Fuzzy Logic [12]. Others propose solutions based on the on-line condition monitoring method which is applied to heavy process industries [13].…”

Section: Several Methods Have Been Developed For the Identification Omentioning

confidence: 99%

See 1 more Smart Citation

Fault Eccentricity Diagnosis in Variable Speed Induction Motor Drive Using DWT

Reda¹,

fayçal²,

Bahi³

2017

AMA_C

View full text Add to dashboard Cite

This paper describes the monitoring and diagnosis of eccentricity fault in variable speed induction motor drive. The used control technique is the indirect field oriented control (IFOC) fuzzy logic based controller to ensure the robust speed regulation and to compensate the fault effects. The variable speed induction motor can be affected by various kinds of faults. Airgap eccentricity is one of the major defects occurring in such electric drives; its detection could be useful for preventing potential catastrophic failures. A dynamic model taking into account the faults is proposed based on the approach of magnetically coupled coils to simulate the behavior of eccentricity faults in induction motor. This work presents two approaches for diagnosis and detection of eccentricity faults and evaluation of their severity based on monitoring of the stator current signals, using Park vector method and discrete wavelet transform (DWT) with different approaches to distinguish healthy as well as faulty conditions of the machine. The obtained simulation results via the proposed technique allow detection and diagnosis of eccentricity fault and identify their severity.

show abstract

Section: Several Methods Have Been Developed For the Identification Omentioning

confidence: 99%

“…The stator current signal contains information included in each frequency band which is resulting from the wavelet packet decomposition. The energy value for each frequency band is defined by [10], [15]:…”

Section: Wavelet Energymentioning

confidence: 99%

Fault Eccentricity Diagnosis in Variable Speed Induction Motor Drive Using DWT

Reda¹,

fayçal²,

Bahi³

2017

AMA_C

View full text Add to dashboard Cite

show abstract

“…Papers [16,17] have also proposed some fault diagnosis methods for coil currents. Neural network (NN) has been widely used in fault diagnosis, the drawbacks of the traditional NN include slow convergence rate and easy to be trapped into local minimum [18][19][20]. In order to remedy the defects of the traditional NN, a fault diagnosis method based on wavelet function and NN has been applied in [21].…”

Section: Introductionmentioning

confidence: 99%

Typical current modelling and feature extraction of high voltage circuit breaker towards condition analysis and fault diagnosis

Shi

et al. 2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…To overcome the nonlinearity and nonstationarity constraints in rubbing fault feature extraction and diagnosis, many techniques based on time-frequency domain analysis (TFA) have been introduced over the last decade [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 ]. Yanjun et al [ 4 ] proposed wavelet packet eigenvalue calculation as a feature extraction technique for rubbing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

“…Similar limitations of the wavelet transform were reported by other researchers [ 7 ]. It is usually not easy to choose the optimal wavelet function for a complex and nonlinear signal, and since the process of determining a proper wavelet function requires a series of experiments, one can conclude that some subjectivity is present in this process [ 8 , 9 ]. Deng et al [ 10 ] introduced a combination of local mean decomposition (LMD) and Teager energy kurtosis (TEK) as a feature extraction technique for rub-impact fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Rub-Impact Fault Diagnosis Using an Effective IMF Selection Technique in Ensemble Empirical Mode Decomposition and Hybrid Feature Models

Prosvirin

Islam

Kim

2018

Sensors

View full text Add to dashboard Cite

The complex nature of rubbing faults makes it difficult to use traditional signal analysis methods for feature extraction. Various time-frequency analysis approaches based on signal decomposition, such as empirical mode decomposition (EMD) and ensemble EMD (EEMD), have been widely utilized recently to analyze rub-impact faults. However, traditional EMD suffers from “mode-mixing”, and in both EMD and EEMD the relevance of the extracted components to rubbing processes must be determined. In this paper, we introduce a new informative intrinsic mode function (IMF) selection method for EEMD and a hybrid feature model for diagnosing rub-impact faults of various intensities. Our method uses a novel selection procedure that combines the degree-of-presence ratio of rub impact and a Kullback–Leibler divergence-based similarity measure into an IMF quality metric with adaptive threshold-based selection to pick the meaningful signal-dominant modes. Signals reconstructed using the selected IMFs contained explicit information about the rubbing faults and are used for hybrid feature extraction. Experimental results demonstrated that the proposed approach effectively defines meaningful IMFs for rubbing processes, and the presented hybrid feature model allows for the classification of rub-impact faults of various intensities with good accuracy.

show abstract

Wavelet transform and neural network techniques for inter-turn short circuit diagnosis and location in induction motor

Cited by 38 publications

References 12 publications

Fault Eccentricity Diagnosis in Variable Speed Induction Motor Drive Using DWT

Fault Eccentricity Diagnosis in Variable Speed Induction Motor Drive Using DWT

Typical current modelling and feature extraction of high voltage circuit breaker towards condition analysis and fault diagnosis

Rub-Impact Fault Diagnosis Using an Effective IMF Selection Technique in Ensemble Empirical Mode Decomposition and Hybrid Feature Models

Contact Info

Product

Resources

About