On-line fault detection method for induction machines based on signal convolution

Cusidó, J.; Romeral, L.; Espinosa, Antonio García; Ramírez, Juan Antonio Ortega; Ruiz, Jordi-Roger Riba

doi:10.1002/etep.455

Cited by 28 publications

(14 citation statements)

References 27 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have published some works on broken rotor bar detection of IM using discrete wavelet transform (DWT) [19][20][21] and wavelet package decomposition (WPD) [8,22]. A few works has been reported on CWT for fault detection of IM [2,16,17]. However, in [2,16,17] the CWT was not adaptive in nature and authors analysed a single phase stator current signal which is not enough to detect the motor faults accurately.…”

Section: Introductionmentioning

confidence: 97%

“…A few works has been reported on CWT for fault detection of IM [2,16,17]. However, in [2,16,17] the CWT was not adaptive in nature and authors analysed a single phase stator current signal which is not enough to detect the motor faults accurately.…”

Section: Introductionmentioning

confidence: 98%

“…Traditionally, fast Fourier transform (FFT) method is widely used for fault detection purpose [9] . However, in FFT the rotor fault detection depends on the accuracy of extracted fault frequencies, and it does not satisfy the appropriate accuracy in the case of load variation and speed changes, as the slip frequency varies with these variations [2,[16][17][18]. In addition, with FFT it is not possible to evaluate the frequency detection on-line during transient state.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On line trained fuzzy logic and adaptive continuous wavelet transform based high precision fault detection of IM with broken rotor bars

Saghafinia

Kahourzade

Mahmoudi

et al. 2012

2012 IEEE Industry Applications Society Annual Meeting

View full text Add to dashboard Cite

This paper presents an online trained fuzzy logic and adaptive wavelet based high precision fault detection of broken rotor bars for squirrel cage induction motor (IM). Motor faults which consist of broken rotor bars, bearing decay, eccentricity, etc. appears as different frequencies in the stator current signals. The winding function is used to obtain stator current and speed signals at different fault and load conditions. These signals are analysed through the adaptive continuous wavelet transform (CWT) to detect the amplitudes and frequency components corresponding to different fault and load conditions. The coefficients of CWT are adapted online based on the harmonics amplitude, which are the output of CWT. These amplitudes and frequencies are applied to train a fuzzy logic controller (FLC) in simulation. Then the adaptive CWT and trained FLC are applied to detect the fault condition of a large size motor in both simulation and realtime. The experimental results found that the proposed adaptive CWT and FLC based fault detection method can detect the motor fault conditions accurately. Thus, the proposed method could be a potential candidate to detect the motor fault, especially for large size industrial motors. Index Terms: adaptive continuous wavelet transform, fault detection, squirrel cage induction motor, fuzzy logic controller, broken rotor bars.

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On line trained fuzzy logic and adaptive continuous wavelet transform based high precision fault detection of IM with broken rotor bars

Saghafinia

Kahourzade

Mahmoudi

et al. 2012

2012 IEEE Industry Applications Society Annual Meeting

View full text Add to dashboard Cite

show abstract

“…Wavelets have been the final solution to these concerns. The authors have discussed numerous works using wavelets for FD . They have given the research works based on the application of continuous wavelet transform, DWT, wavelet packet transform, and second‐generation wavelet transform for FD.…”

Section: Introductionmentioning

confidence: 99%

Detection and diagnosis of induction motor bearing faults using multiwavelet transform and naive Bayes classifier

Saini

Aggarwal

2018

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary A novel framework is proposed for the classification of motor bearing faults by using multiwavelet transform and naive Bayes classifier. This work has explored the application of multiwavelet transform to the vibration signatures for extracting the effective fault features. Geronimo‐Hardin‐Massopust multiwavelet filter bank has been employed in this work for multiresolution analysis up to fourth decomposition level. This work has relied upon multiwavelets as the multiwavelets are enriched with the properties which wavelets do not offer simultaneously like compact support and orthogonality without compromising with symmetricity and higher order of vanishing moments. After that, fault features have been extracted from the decomposed vibration signals to utilize the fault information present at different resolution levels. The fault classification has been accomplished with high success rate by using the extracted fault features with the naive Bayes classifier due to its inherent features like robustness to noise, simplicity, and quick convergence even with less training data. The efficacy of the proposed classifier has been verified with both the offline signals and the real‐time signals having different fault severity levels. The outperformance of the proposed classifier has been shown by comparing the classification results with other established supervised classification techniques like probabilistic neural network, Gaussian‐support vector machine, polynomial‐support vector machine, and linear‐support vector machine.

show abstract

“…In [11], the effects of the broken bar location have been studied, and it has been shown that the distribution of broken bars in different poles leads to the decrease in amplitude of side-band components in stator-current profiles. In [25], the convolution of wavelet-based functions of stator currents has been utilized for fault diagnosis in stationary and non-stationary motor conditions. It has been shown that ignoring the existence of inherent eccentricity due to manufacturing and installation procedure leads to error in precise broken bar fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Pattern recognition for broken bars fault diagnosis in induction motors under various supply conditions

Ebrahimi

Faiz

Akin

2011

Int Trans Elec Energy Syst

View full text Add to dashboard Cite

SUMMARY In this paper, impacts of the unbalanced voltage supply conditions and inverter harmonics on accurate broken bar fault diagnosis in induction motors are investigated in detail. It is presented that amplitude of the side‐band components at frequencies (1 ± 2ks)fs as a well‐known index is not competent for accurate broken bar fault detection in induction motors in the presence of unbalanced voltage supply. Thus, the above mentioned frequency pattern is modified for precise broken bar fault recognition in induction motors under unbalanced voltage supply conditions. Amplitude of the side‐band components at frequencies [k/p(1 − s) ± s]fs is proposed as a proper index for precise broken bar fault identification in the aforementioned conditions. In order to evaluate proposed index competency, effects of the load variation and unbalanced supply deviation on the proposed index are analyzed. Furthermore, electromotive force of the healthy and faulty induction motors has been calculated, and side‐band components at frequencies [k/p(1 − s) ± s]fs are extracted from the electromotive force spectra which is nominated as a new technique for precise broken bar fault recognition in induction motors. Comparison of simulation and experimental results verifies the method's ability to detect broken bars with an unbalanced voltage supply and inverter harmonics. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

On-line fault detection method for induction machines based on signal convolution

Cited by 28 publications

References 27 publications

On line trained fuzzy logic and adaptive continuous wavelet transform based high precision fault detection of IM with broken rotor bars

On line trained fuzzy logic and adaptive continuous wavelet transform based high precision fault detection of IM with broken rotor bars

Detection and diagnosis of induction motor bearing faults using multiwavelet transform and naive Bayes classifier

Pattern recognition for broken bars fault diagnosis in induction motors under various supply conditions

Contact Info

Product

Resources

About