Bearing fault diagnosis of a three phase induction motor using stockwell transform
01 Dec 2016-pp 1-6
TL;DR: In this paper, the S-transform based feature extraction can be effectively utilized for bearing fault detection and diagnosis in a three phase induction motor using Stockwell transform of stator currents.
Abstract: This paper presents bearing fault detection and its diagnosis in a three phase induction motor using Stockwell transform of stator currents. The maximum magnitude and maximum phase angle plots are obtained from S-transform for various bearing conditions both on shaft-side and fan-side. The standard deviation of these plots are utilized to detect and analyze the bearing faults. The various bearing faults analyzed under case studies include defects in innerrace, outerrace, cage and balls. The experimental study shows that the S-transform based feature extraction can be effectively utilized for bearing fault detection and diagnosis in three phase induction motor.
Citations
More filters
TL;DR: F faulty bearing detection, classification and its location in a three-phase induction motor using Stockwell transform and Support vector machine is presented.
55 citations
4 citations
01 Jun 2018
TL;DR: This paper presents a technique to locate defective bearing based on Stockwell Transform of stator current signals and has been tested successfully for the bearing faults such as ball and outerrace fault.
Abstract: The rotor shaft of a three-phase induction motor is suspended on two bearings; one on fan-side, other on load-side. This paper presents a technique to locate defective bearing based on Stockwell Transform of stator current signals. The statistical properties of Stockwell transform of current signals are used to form feature vector. Principal Component Analysis is used to extract components with high variability from this feature vector. The top principal components thus extracted, are utilized to locate the defective bearing with the help of Support Vector Machine. The proposed algorithm has been tested successfully for the bearing faults such as ball and outerrace fault.
Cites methods from "Bearing fault diagnosis of a three ..."
...Defective bearings in a three-phase induction motor can be effectively located by analyzing the stator currents with the help of Stockwell Transform....
[...]
...Stockwell Transform (ST) [21] is a phase-corrected version of Continuous Wavelet Transform (CWT) which uses Gaussian window as its mother wavelet....
[...]
...The stator current signals are analyzed with Stockwell Transform (ST) which results in a ST matrix....
[...]
...Among these statistical features, standard deviation (SD) is reported to be useful parameter in bearing fault diagnosis based on Stockwell Transform [14]....
[...]
...In this paper, an effort has been made to locate the defective bearing using Support Vector Machine (SVM) which is fed with principal components obtained from Stockwell Transform of stator current signals....
[...]
01 Jan 2019
TL;DR: S-Transformation, which is superior as compared to CWT and STFT as it does not contain any cross terms, is used for bearing fault detection, and random forest, an algorithm which is easy to implement and requires minimum memory, are used for detection of external faults.
Abstract: Induction motors are extensively used motor type for various industrial applications for the reason that they are robust, simple in structure, and efficient. On the other hand, induction motors are prone to different faults during their lifetime due to hostile environments. If the fault is not detected in its rudimentary phase, it may cause unexpected shut down of the entire system and colossal loss in industry. It is conspicuous that scope of this field is huge. This work presents detection of internal and external faults of induction motor. S-Transformation, which is superior as compared to CWT and STFT as it does not contain any cross terms, is used for bearing fault detection, and random forest, an algorithm which is easy to implement and requires minimum memory, is used for detection of external faults. The fault can be detected with more accuracy in premature state leads to improve the reliability of the system.
TL;DR: In this paper , the authors proposed spectral analysis of stator current to estimate motor faults, FFT analysis is commonly preferred, but the problems associated with normal FFT analyses will mislead the fault diagnosis, and each technique requires special attention to get good results.
Abstract: Detection of bearing faults have become crucial in electrical machines, particularly in induction motors. Conventional monitoring procedures using vibration sensors, temperature sensors, etc. are costly and need more tests to estimate the nature of fault. Hence, the current monitoring attracts the concentration of many industries for continuous monitoring. Spectral analysis of stator current to estimate motor faults, FFT analysis, is commonly preferred. But the problems associated with normal FFT analysis will mislead the fault diagnosis. Therefore, advanced spectral methods like wavelet transforms, matrix pencil method, MUSIC algorithm, s-transforms have been proposed. But each technique requires special attention to get good results. On the other hand, faults experienced by the induction motor can be categorized into bearing-related, rotor- and stator-related, and eccentricity. Among these faults, bearing damage accounts for 40-90% and requires additional concentration to estimate.
References
More filters
12 Jul 2014
TL;DR: In this article, the authors used Discrete Wavelet Transform (DWT) and Multi Resolution Analysis (MRA) to analyze any signal for obtaining better resolution of signal energy.
Abstract: Squirrel Cage Induction Motor (SCIM) is largely prevalent machine which are in employment for conversion of electrical energy into mechanical energy in an assorted nature of applications. Bearings are most symptomatic components of mechanical faults occurring in SCIM as they are held accountable for 40-50 % of all the motor malfunctions. Fast Fourier Transform (FFT) is an imperative spectrum estimation technique, comprehensively used with Motor Current Signature Analysis (MCSA). However FFT does not endow with substantial outcome when frequency resolution is considered. Multi Resolution Analysis (MRA) can be used to analyze any signal for obtaining better resolution. Discrete Wavelet Transform (DWT) gives out better idea about the variation in specific frequency band all through the bearing fault(s). In this paper, for minimalism and fast analysis, signal energy is calculated. The stator current data is acquired by creating different fault cases on a 3-phase, 1.5kW, 4P, and 1440 RPM induction motor. The variation in the energy of healthy and energy of faulty condition(s) bestow with a better idea pertaining to fault detection and classification. Actual data analysis divulges that FFT is not suitable for practical circumstances. After analyzing different cases of bearing fault, it can evidently be concluded that DWT has an edge over FFT. Some attributes regarding bearing fault classification are also obtained.
15 citations
"Bearing fault diagnosis of a three ..." refers methods in this paper
...Discrete wavelet transform was used to decompose stator currents to characterize and detect bearing faults in [13], [14]....
[...]
24 Oct 2013
TL;DR: In this paper, the authors presented a predicability analysis method based on relative entropy measures estimated over reconstructed signals obtained from wavelet-packet decomposition components, which were simulated using a real motor current signal with addition of frequency components related to the bearing faults.
Abstract: Fault detection in electrical machines have been widely explored by researchers, especially bearing faults that represents about 40% to 60% of the total faults. Since this kind of fault is detectable by particular frequencies at the stator current, it is now a source of investigation. Thus, this work presents a predicability analysis method based on relative entropy measures estimated over reconstructed signals obtained from wavelet-packet decomposition components. The signals were simulated using a real motor current signal with addition of frequency components related to the bearing faults. Using three ANN topologies, these entropy measures are classified in two groups: normal and faulty signals with a high performance rate.
15 citations
"Bearing fault diagnosis of a three ..." refers methods in this paper
...In [10], [11] predictability analysis based on relative entropy, bhattacharyya distance was performed on wavelet components using WPD on stator currents....
[...]
01 May 2007
TL;DR: This method involves the decomposition of motor current into equally spaced frequency bands by using all-pass implementation of Elliptic IIR half-band filters in the filter bank structure to obtain wavelet packet coefficients (WPC).
Abstract: We present a method for detecting motor bearing fault conditions via wavelet packet decomposition (WPD) of induction motor current. This method involves the decomposition of motor current into equally spaced frequency bands by using all-pass implementation of Elliptic IIR half-band filters in the filter bank structure to obtain wavelet packet coefficients (WPC). Then, the bias in WPCs for each frequency band is removed to suppress leakage from adjacent frequency bands. Fourier analysis is applied to wavelet packet coefficients to provide higher frequency resolution within each frequency band. The changes in the energy levels of frequency bands in which motor fault related current frequencies lie are monitored to detect motor fault conditions.
15 citations
"Bearing fault diagnosis of a three ..." refers methods in this paper
...Wavelet packet decomposition (WPD) technique was used to analyze stator currents in defect frequency bands to detect faulty bearings in [7], [8]....
[...]
01 Aug 2006
TL;DR: MCSA is a noninvasive on line monitoring technique to diagnose faults in three-phase IM by differences detection between fault and normal conditions, in current spectrum.
Abstract: This paper deals with the application of CSA for detection of bearing damage on induction motor. Three-phase IM are the "workhorses" of industry and are the most widely used electrical machines. In industrialized nations, 70% of industrial processes use the induction motor. For this reason, detection of incipient motor failures is very important, thereby avoiding production lost and reducing operational costs. The main idea of motor damage detection leads with "motor variables, currents, flux, electric torque and power, variations (in particular the spectrum) with respect to the normal time-varying operating conditions of the motor". MCSA is a noninvasive on line monitoring technique to diagnose faults in three-phase IM by differences detection between fault and normal conditions, in current spectrum. Experimental tests were realized in IM of small power, and the results will be validated in later works with a representative quantity of motors.
12 citations
01 Jan 2006
TL;DR: In this article, the application of CSA for detection of bearing damage on an induction motor is discussed, where the main idea of motor damage detection leads with motor variables, currents, flux, electric torque and power, variations with respect to the normal time-varying operating conditions of the motor.
Abstract: This paper deals with the application of CSA for detection of bearing damage on induction motor. Three-phase IM are the "workhorses" of industry and are the most widely used electrical machines. In industrialized nations, 70% of industrial processes use the induction motor. For this reason, detection of incipient motor failures is very important, thereby avoiding production lost and reducing operational costs. The main idea of motor damage detection leads with "motor variables, currents, flux, electric torque and power, variations (in particular the spectrum) with respect to the normal time-varying operating conditions of the motor". MCSA is a noninvasive on line monitoring technique to diagnose faults in three-phase IM by differences detection between fault and normal conditions, in current spectrum. Experimental tests were realized in IM of small power, and the results will be validated in later works with a representative quantity of motors
10 citations