Mourad Kedadouche

Monitoring Machines by Using a Hybrid Method Combining MED, EMD, and TKEO

Amplitude demodulation is a key for diagnosing bearing faults. The quality of the demodulation determines the efficiency of the spectrum analysis in detecting the defect. A signal analysis technique based on minimum entropy deconvolution (MED), empirical mode decomposition (EMD), and Teager Kaiser energy operator (TKEO) is presented. The proposed method consists in enhancing the signal by using MED, decomposing the signal in intrinsic mode functions (IMFs) and selects only the IMF which presents the highest correlation coefficient with the original signal. In this study the first IMF1 was automatically selected, since it represents the contribution of high frequencies which are first excited at the early stages of degradation. After that, TKEO is used to track the modulation energy. The spectrum is applied to the instantaneous amplitude. Therefore, the character of the bearing faults can be recognized according to the envelope spectrum. The simulation and experimental results show that an envelope spectrum analysis based on MED-EMD and TKEO provides a reliable signal analysis tool. The experimental application has been developed on acoustic emission and vibration signals recorded for bearing fault detection.

Empirical Mode Decomposition of Acoustic Emission for Early Detection of Bearing Defects

Empirical Mode Decomposition (EMD) is one of the techniques that proved its efficiency for an early detection of defects in many mechanical applications like bearings and gears. The EMD methodology decomposes the original times series data into intrinsic mode functions (IMF), by using the Hilbert-Huang transform. In this study, EMD is applied to acoustic emission signals. The acoustic emission signal is heterodynined around a central high frequency in order to obtain an audible signal. Scalar statistical parameters such as Kurtosis and THIKAT are then used in this study. These statistical descriptors are calculated for each IMF. The technique is validated by experiments on a test bench with a very small crack (40 μm) on the outer race of a ball bearing. It is found that the application of time descriptors to different IMF decomposition levels gives good results for early detection of defects in comparison with the original time signal.

Fault feature extraction and classification based on WPT and SVD: Application to element bearings with artificially created faults under variable conditions:

Achieving a precise fault diagnosis for rolling bearings under variable conditions is a problematic challenge. In order to enhance the classification and achieves a higher precision for diagnosing rolling bearing degradation, a hybrid method is proposed. The method combines wavelet packet transform, singular value decomposition and support vector machine. The first step of the method is the decomposition of the signal using wavelet packet transform and then instantaneous amplitudes and energy are computed for each component. The Second step is to apply the singular value decomposition to the matrix constructed by the instantaneous amplitudes and energy in order to reduce the matrix dimension and obtaining the fault feature unaffected by the operating condition. The features extracted by singular value decomposition are then used as an input to the support vector machine in order to recognize the fault mode of rolling bearings. The method is applied to a bearing with faults created using electro-discharge machining under laboratory conditions. Test results show that the proposed methodology is effective to classify rolling bearing faults with high accuracy.

Nonlinear Parameters for Monitoring Gear: Comparison Between Lempel-Ziv, Approximate Entropy, and Sample Entropy Complexity

Vibration analysis is the most used technique for defect monitoring failures of industrial gearboxes. Detection and diagnosis of gear defects are thus crucial to avoid catastrophic failures. It is therefore important to detect early fault symptoms. This paper introduces signal processing methods based on approximate entropy (ApEn), sample entropy (SampEn), and Lempel-Ziv Complexity (LZC) for detection of gears defects. These methods are based on statistical measurements exploring the regularity of vibratory signals. Applied to gear signals, the parameter selection of ApEn, SampEn, and LZC calculation is first numerically investigated, and appropriate parameters are suggested. Finally, an experimental study is presented to investigate the effectiveness of these indicators and a comparative study with traditional time domain indicators is presented. The results demonstrate that ApEn, SampEn, and LZC provide alternative features for signal processing. A new methodology is presented combining both Kurtosis and LZC for early detection of faults. The results show that this proposed method may be used as an effective tool for early detection of gear faults.

Bearing Fault Feature Extraction Using Autoregressive Coefficients, Linear Discriminant Analysis and Support Vector Machine Under Variable Operating Conditions

Advanced monitoring requires automatic diagnosis of machines operating under variable conditions. In this paper, an intelligent method is introduced in order to enhance the classification and achieves a higher precision for the diagnosis of degradation of rolling bearings operating under condition variations. The method uses the coefficients of autoregressive modeling (AR) of the bearing vibration signal as the features of a classifier. A Linear Discriminant Analysis (LDA) of the matrix feature obtained from AR analysis is applied in order to extract the components that discriminate the different fault modes since it is insensitive to the working conditions. Finally, the results obtained from LDA are used as the input of a support Vector Machine (SVM) classifier to automatically identify the bearing state. The experimental results show that the performance of the proposed method is effective and achieve a good accuracy.

Empirical Mode Decomposition Combined with Empirical Wavelets for Extracting Bearing Frequencies in a Noisy Environment and Early Detection of Defects

The amplitude demodulation of a bearing signal allows for the extraction of component information-carrying defects on rotary machines. However, the quality of the demodulated signal depends on the selected frequency band for demodulation. Kurtogram is widely used to detect the frequency bandwidth which is the most excited by a defect. However in presence of high noises, the Kurtogram may be deficient in effectively detecting the resonances and it presents some instabilities. In the last decade, the Empirical Mode Decomposition (EMD) technique has been used by a lot of researchers for the signal decomposition. In this study, the EMD and Empirical Wavelet (EW) are used to generate a new feature. The EW is used to generate a filter bank which depends on the content of the component frequencies of the signal. A segmentation of the spectrum to define the support boundaries of the filter is proposed. The new indicator is proposed in order to track the frequency band that is more excited by a bearing fault. This study shows that the proposed technique can detect the resonances in all cases of simulation. On the other hand, the proposed method is able first to detect the resonance frequencies and secondly to detect on which Intrinsic Mode Function (IMF), the bearing default occurs. The proposed technique has confirmed its effectiveness by testing it on experimental signals obtained from a test bench with defects on a bearing outer race. A defect of only 40 μ on the outer race has been detected, which makes this method very effective for an early detection of bearing defects.