Intelligent Fault Diagnosis of Rolling Element Bearing Based on SVMs and Statistical Characteristics

2007 ◽  
Author(s):  
Junyan Yang ◽  
Youyun Zhang ◽  
Yongsheng Zhu ◽  
Qinghua Wang
Keyword(s):  
Frequency Domain ◽  
Wavelet Packet ◽  
Classification Performance ◽  
Rolling Element Bearing ◽  
Statistical Characteristics ◽  
Wavelet Packet Decomposition ◽  
Frequency Bands ◽  
Time Frequency ◽  
Rolling Element ◽  
Element Bearing

In this paper, the statistical characteristics of time, frequency and time-frequency domain are applied to discriminate various fault types and evaluate various fault conditions of rolling element bearing, and the classification performance of them is evaluated by using SVMs. Experimental results showed that the statistical characteristics Mean, Variance, Root, RMS and Peak of the 25 sub frequency bands in frequency domain obtain higher classification accuracy rate on all the fault datasets than the statistical characteristics in the whole time and frequency domain. Wavelet packet decomposition is an efficient time-frequency analysis tool, and it can decompose the original signal into independent frequency bands. Experiment on the statistical characteristics of the 5th level wavelet packet decomposition showed that the statistical characteristics Variance, Root, RMS and Peak can discriminate various fault types and evaluate various fault conditions well on all the datasets. Compared with the statistical characteristics of sub frequency bands in frequency domain, the classification performance of the statistical characteristics of the wavelet packet transform is a little lower than that of the statistical characteristics of sub frequency bands in frequency domain.

Rolling element bearing weak feature extraction based on improved optimal frequency band determination

2018 ◽  
Vol 233 (2) ◽  
pp. 623-634 ◽  
Author(s):  
Rui Yang ◽  
Hongkun Li ◽  
Chaoge Wang ◽  
Changbo He
Keyword(s):  
Frequency Domain ◽  
Frequency Band ◽  
Signal To Noise Ratio ◽  
Wavelet Packet ◽  
Rolling Element Bearing ◽  
Optimal Frequency ◽  
Filter Length ◽  
Iteration Period ◽  
Rolling Element ◽  
Element Bearing

Conventional Kurtosis method represents the statistical property of signal in the time domain. Correlated Kurtosis is proposed that combines the correlation coefficient and Kurtosis in order to indicate the periodicity and impact of signal. In this study, correlated Kurtosis is introduced into frequency domain to improve the recognition accuracy of the optimal frequency band. It does not perform well under the lower signal-to-noise ratio. And then, maximum correlation Kurtosis de-convolution method is used for extracting the approximate impact signal before selecting the optimal frequency band. However, it is limited in diagnosing rolling element bearing fault in the case of the algorithm iteration period is unknown. In addition, filter length also affects the filtering results. To eliminate the confusion, correlated Kurtosis of the frequency domain is applied to iteration period calculation. In this research, a new index is also proposed based on entropy and correlated Kurtosis to optimize the filter length. Then, the full bandwidth of filtered signal is partitioned into several sub-bands according to the refined wavelet packet binary tree. The correlated Kurtosis for each sub-band is calculated. The optimal sub-band for which the correlated Kurtosis is maximal is extracted to analysis. In the end, the efficiency of the new index and the fault diagnosis method are verified by using simulation data and experimental data.

A multichannel fusion approach based on coupled hidden Markov models for rolling element bearing fault diagnosis

2011 ◽  
Vol 226 (1) ◽  
pp. 202-216 ◽  
Author(s):  
W B Xiao ◽  
J Chen ◽  
G M Dong ◽  
Y Zhou ◽  
Z Y Wang
Keyword(s):  
Markov Models ◽  
Hidden Markov ◽  
Wavelet Packet ◽  
Rolling Element Bearing ◽  
Vibration Signals ◽  
Bearing Fault Diagnosis ◽  
Rolling Element ◽  
Coupled Hidden Markov Models ◽  
Element Bearing ◽  
Fusion Approach

This paper presents a novel multichannel fusion approach based on coupled hidden Markov models (CHMMs) for rolling element bearing fault diagnosis. Different from a hidden Markov model (HMM), a CHMM contains multiple state sequences and observation sequences, and hence has powerful potential for multichannel fusion. In this study, a two-chain CHMM is employed to integrate the two-channel vibration signals collected from bearings, i.e. the horizontal and vertical vibration signals. Efficient probabilistic inference and parameter estimation algorithms are developed for the model. An experiment was carried out to validate the proposed approach. Normalized wavelet packet energy and wavelet packet energy entropy are extracted as features for classification respectively. Then, the results of the proposed approach are compared with those of the currently used approach based on HMMs and one-channel signals. The results show that the proposed approach is feasible and effective to improve the classification rate.

scholarly journals Time–Frequency Domain Characteristics of Acoustic Emission Signals and Critical Fracture Precursor Signals in the Deep Granite Deformation Process

2021 ◽  
Vol 11 (17) ◽  
pp. 8236
Author(s):  
Le Zhang ◽  
Hongguang Ji ◽  
Liyuan Liu ◽  
Jiwei Zhao
Keyword(s):  
Acoustic Emission ◽  
Frequency Domain ◽  
High Frequency ◽  
Wavelet Packet ◽  
Confining Pressure ◽  
Wavelet Packet Decomposition ◽  
Evolution Law ◽  
Time Frequency ◽  
Characteristic Signal ◽  
Failure Precursor

To study the crack evolution law and failure precursory characteristics of deep granite rocks in the process of deformation and failure under high confining pressure, granite samples obtained from a depth of 1150 m are tested using a TAW-2000 triaxial hydraulic servo testing machine and a PCI-II acoustic emission monitoring system. Based on the stress–strain curve and IET function, the loading process of the sample is divided into five stages: crack closure, linear elastic deformation, microcrack generation and development, macroscopic fracture generation and energy surge, and post-peak failure. The evolution trend and fracture evolution law of the acoustic emission signal event interval function in different stages are analyzed. In particular, the signals with an amplitude greater than 85 dB, a peak frequency greater than 350 kHz, and a frequency centroid greater than 275 kHz are defined as the failure precursor signals before the rock reaches the peak stress. The defined precursor signal conditions agree well with the experimental results. The time–frequency analysis and wavelet packet decomposition of the precursor signal are performed on the extracted characteristic signal of the failure precursor. The results show that the time-domain signal is in the form of a continuous waveform, and the frequency-domain waveform has multi-peak coexistence that is mainly concentrated in the high-frequency region. The energy distribution obtained by the wavelet packet decomposition of the characteristic signal is verified with the frequency-domain waveform. The energy distribution of the signal is mainly concentrated in the 343.75–375 kHz frequency band, followed by the 281.25–312.5 kHz frequency band. The energy proportion of the high-frequency signal increases with the confining pressure.

scholarly journals Estimation of the Defect Width on the Outer Race of a Rolling Element Bearing under Time-Varying Speed Conditions

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Guang-Quan Hou ◽  
Chang-Myung Lee
Keyword(s):  
Research Work ◽  
Defect Size ◽  
Remaining Useful Life ◽  
Rolling Element Bearing ◽  
Time Varying ◽  
Entry And Exit ◽  
Outer Race ◽  
Time Frequency ◽  
Rolling Element ◽  
Element Bearing

Fault diagnosis and failure prognostics for rolling element bearing are helpful for preventing equipment failure and predicting the remaining useful life (RUL) to avoid catastrophic failure. Spall size is an important fault feature for RUL prediction, and most research work has focused on estimating the fault size under constant speed conditions. However, estimation of the defect width under time-varying speed conditions is still a challenge. In this paper, a method is proposed to solve this problem. To enhance the entry and exit events, the edited cepstrum is used to remove the determined components. The preprocessed signal is resampled from the time domain to the angular domain to eliminate the effect of speed variation and measure the defect size of a rolling element bearing on outer race. Next, the transient impulse components are extracted by local mean decomposition. The entry and exit points when the roller passes over the defect width on the outer race were identified by further processing the extracted signal with time-frequency analysis based on the continuous wavelet transform. The defect size can be calculated with the angle duration, which is measured from the identified entry and exit points. The proposed method was validated experimentally.

Wavelet Analysis and Envelope Detection For Rolling Element Bearing Fault Diagnosis—Their Effectiveness and Flexibilities

2001 ◽  
Vol 123 (3) ◽  
pp. 303-310 ◽  
Author(s):  
Peter W. Tse ◽  
Y. H. Peng ◽  
Richard Yam
Keyword(s):  
Fault Diagnosis ◽  
Wavelet Analysis ◽  
Rolling Element Bearing ◽  
Frequency Spectra ◽  
Bearing Faults ◽  
Time Frequency ◽  
Envelope Detection ◽  
Rolling Element ◽  
Element Bearing ◽  
Bearing Characteristic

The components which often fail in a rolling element bearing are the outer-race, the inner-race, the rollers, and the cage. Such failures generate a series of impact vibrations in short time intervals, which occur at Bearing Characteristic Frequencies (BCF). Since BCF contain very little energy, and are usually overwhelmed by noise and higher levels of macro-structural vibrations, they are difficult to find in their frequency spectra when using the common technique of Fast Fourier Transforms (FFT). Therefore, Envelope Detection (ED) is always used with FFT to identify faults occurring at the BCF. However, the computation of ED is complicated, and requires expensive equipment and experienced operators to process. This, coupled with the incapacity of FFT to detect nonstationary signals, makes wavelet analysis a popular alternative for machine fault diagnosis. Wavelet analysis provides multi-resolution in time-frequency distribution for easier detection of abnormal vibration signals. From the results of extensive experiments performed in a series of motor-pump driven systems, the methods of wavelet analysis and FFT with ED are proven to be efficient in detecting some types of bearing faults. Since wavelet analysis can detect both periodic and nonperiodic signals, it allows the machine operator to more easily detect the remaining types of bearing faults which are impossible by the method of FFT with ED. Hence, wavelet analysis is a better fault diagnostic tool for the practice in maintenance.

scholarly journals Rolling Element Bearing Condition Monitoring using Filtered Acoustic Emission

2018 ◽  
Vol 8 (5) ◽  
pp. 3560
Author(s):  
Sudarsan Sahoo ◽  
J. K. Das ◽  
Bapi Debnath
Keyword(s):  
Condition Monitoring ◽  
Acoustic Signal ◽  
Rolling Element Bearing ◽  
Time Frequency ◽  
Second Stage ◽  
Acoustic Signature ◽  
Bearing Condition Monitoring ◽  
Rolling Element ◽  
Element Bearing ◽  
Two Stages

The defect present in the bearing of a rolling element may affect the performance of the rotating machinery and may reduce its efficiency. For this reason the condition monitoring of a rolling element bearing is very essential. So many measuring parameters are there to diagnose the fault in a rolling element bearing. Acoustic signature monitoring is one of them. Every rolling element bearing has its own acoustic signature when it is in healthy condition and when the bearing get defected then there is a change in its original acoustic signature. This change in acoustic signature can be monitored and analyzed to detect the fault present in the bearing. But the noise present in the acquired acoustic signal may affect the analysis. So the noisy acoustic signal must be filtered before the analysis. In this work the experiment is performed in two stages. In first stage the filtration of the acquired acoustic signal is done by employing the active noise cancellation (ANC) filtering techniques. In second stage the filtered signal is used for the further analysis. For the analysis initially the static analysis is done and then the frequency and the time-frequency analysis is done to diagnose the defect in the bearing. From all the three analysis the information about the defect present in the bearing is well detected.

A Novel Fault Diagnosis Method Based on Time-Frequency Image Recognition

2014 ◽  
Vol 687-691 ◽  
pp. 3569-3573 ◽  
Author(s):  
Wei Gang Wang ◽  
Zhan Sheng Liu
Keyword(s):  
Fault Diagnosis ◽  
Image Recognition ◽  
Rolling Element Bearing ◽  
Support Vector ◽  
Time Frequency ◽  
Rolling Element ◽  
Diagnosis Method ◽  
Element Bearing ◽  
Vibration Time ◽  
Pyramid Matching

A novel intelligent fault diagnosis method based on vibration time-frequency image recognition is proposed in this paper. First, Smooth pseudo Wigner-Ville distribution (SPWVD) is employed to represent the time-frequency distribution characteristics. Then, the features of time-frequency images are extracted by using locality-constrained linear coding (LLC) and spatial pyramid matching. Next, we use the support vector machine to identify these feature vectors for realizing intelligent fault detection. The promise of our algorithm is illustrated by performing above procedures on the vibration signals measured from rolling element bearing with sixteen operating states. Experimental results show that the proposed method can acquire higher diagnosis accuracy compared with the ScSPM method in rolling element bearing diagnosis.

Sign in / Sign up

Export Citation Format

Share Document