Efficient vibration analysis system using empirical mode decomposition residual signal and multi-axis data

In order to improve the accuracy of rail crack detection, especially for the high-speed condition, this paper proposes a rail crack detection method based on the adaptive noise cancellation method of empirical mode decomposition (EMD). The acoustic emission (AE) signals of simulated crack signals are obtained by the rail-wheel test rig, and these signals are decomposed into intrinsic mode functions (IMFs) by EMD. The cross-correlation analysis is used to reserve the IMFs which contains useful information. Then, the denoising signals are reconstructed based on the reserved IMFs, and wavelet transform is employed to detect the crack signals from the denoising signals. Signals at different speeds are investigated by the proposed method and the interference of noise signals is suppressed effectively. The results illustrate that the proposed method can detect the rail crack signals effectively at high speed with noise.

A brainwave classification, which does not involve any limb movement and stimulus for character-writing applications, benefits impaired people, in terms of practical communication, because it allows users to command a device/computer directly via electroencephalogram signals. In this paper, we propose a new framework based on Empirical Mode Decomposition (EMD) features along with the Gaussian Mixture Model (GMM) and Kernel Extreme Learning Machine (KELM)-based classifiers. For this purpose, firstly, we introduce EMD to decompose EEG signals into Intrinsic Mode Functions (IMFs), which actually are used as the input features of the brainwave classification for the character-writing application. We hypothesize that EMD along with the appropriate IMF is quite powerful for the brainwave classification, in terms of character applications, because of the wavelet-like decomposition without any down sampling process. Secondly, by getting motivated with shallow learning classifiers, we can provide promising performance for the classification of binary classes, GMM and KELM, which are applied for the learning of features along with the brainwave classification. Lastly, we propose a new method by combining GMM and KELM to fuse the merits of different classifiers. Moreover, the proposed methods are validated by using the volunteer-independent 5-fold cross-validation and accuracy as a standard measurement. The experimental results showed that EMD with the proper IMF achieved better results than the conventional discrete wavelet transform (DWT) feature. Moreover, we found that the EMD feature along with the GMM/KELM-based classifier provides the average accuracy of 77.40% and 80.10%, respectively, which could perform better than the conventional methods where we use DWT along with the artificial neural network classifier in order to get the average accuracy of 80.60%. Furthermore, we obtained the improved performance by combining GMM and KELM, i.e., average accuracy of 80.60%. These outcomes exhibit the usefulness of the EMD feature combining with GMM and KELM based classifiers for the brainwave classification in terms of the Character-Writing application, which do not require any limb movement and stimulus.

A novel denoising method based on empirical mode decomposition (EMD) is put forward in this paper. With the new method, the nonlinear and non-stationary signal is decomposed into intrinsic mode functions (IMF) via EMD, then, high frequency IMFs will be processed by threshold denoising approach. The difference between the proposed method and the wavelet transform (WT) is that the EMD method can be applied to nonlinear processes and non-stationary processes adaptively. With the new method, there is no need selecting the base wavelet and it can be applied easily to analyze signals. In order to solve the problem of end effect in EMD, an approach of data extending based on minimum mean-square deviation approach is adopted in the present study. As the result of using the real MEMS signal for experiment the standard deviation was reduced to 0.027 times the original one in new ways. By analyzing the Allan variance, types of noises existing in the signal of MEMS gyro are restrained.

Exhaust gas temperature is one of the important performance characterization parameters of the state of engine. The prediction analysis of the Exhaust Gas Temperature Margin (EGTM) series is helpful to estimate engine’s performance, which can offer theory support for the fault detection and diagnose. Aiming at the non-linear and non-stationary features of EGTM data, a prediction method based on Empirical Mode Decomposition (EMD) and Least Squares Support Vector Regression (LS-SVR) is proposed. The EMD method is used to decompose the EGTM data to reduce the complexity of the time series. The EGTM data were decomposed into Intrinsic Mode Function (IMF) and the residual series by EMD. Finally, the prediction model were build the different LS-SVR for predicting each IMF and the residual series. Each prediction results of the series were combined to obtain EGTM forecast results. The results show that compared with the traditional prediction method, RMSE and MAE are reduced to 2.3178 and 1.8388, which improves the prediction accuracy effectively.

The analysis of electroencephalogram (EEG) signals is becoming more important because of the time-consuming and large bias of traditional visual detection technology, especially in diagnosis of epilepsy. Based on the nonlinear and non-stationary of the EEGs, empirical mode decomposition (EMD) is applied to decompose the original signals into intrinsic mode functions (IMFs). In this paper, after getting the IMFs, the fluctuation index and variation coefficient are calculated to analyze the amplitude change of IMFs. In order to better reflect the information of EEG signals, Hilbert transform is applied to obtain the instantaneous frequency for each IMF. Then, the novel feature named fluctuation index and variation coefficient of instantaneous frequency for IMFs are calculated. Furthermore, feature based on sample entropy of the first order difference is extracted. Finally, both of the calculated features will put together as a fusion feature into SVM for classification. The proposed method is evaluated using the Boon epileptic dataset and the highest average classification accuracy is 99.59%, showing a powerful method to detect seizure.

This paper proposes a new method for bearing fault detection in induction motors by combining Complementary Ensemble Empirical Mode Decomposition (CEEMD) and the Teager-Kaiser Energy Operator (TKEO). The proposed method addresses the challenges of analyzing non-stationary and non-linear signals in motor current signature analysis. CEEMD is employed to decompose the stator current signals into Intrinsic Mode Functions (IMFs), effectively reducing mode mixing issues common in traditional EMD. The TKEO is then applied to extract amplitude and frequency modulations with high temporal resolution, enabling precise identification of fault-specific frequencies. Experimental validation was conducted on a test bench for various bearing fault conditions: inner race, outer race, and ball defects. Results demonstrate that the combination of CEEMD-TKEO successfully detects characteristic fault frequencies with improved accuracy compared to conventional methods. The method identified specific frequency components and their sidebands, correlating with theoretical calculations. Furthermore, correlation coefficient analysis between original signals and their IMFs provided effective mode selection for fault diagnosis. The proposed approach shows promising results for industrial applications, offering both computational efficiency and reliable fault detection capabilities.

Fault classification in power systems using EMD and SVM

Empirical mode decomposition (EMD) is an adaptive method for decomposing a signal into intrinsic mode functions (IMFs).This study explored using EMD of ultrasound imaging for gain-independent measurements on tissue echogenicity. The IMF-based echogenicity ratio (IER) was proposed using the first (C1) and second IMFs (C2) of ultrasound radiofrequency data. Experiments on lipid phantoms were conducted to investigate the practical performance of IER. Phantoms with lipid concentrations 0%–30% (n = 36) were scanned using a clinical ultrasound scanner to acquire the radiofrequency data under different gains (12–33 dB) for EMD and IER calculations. Experiments on a tissue-mimicking phantom were further performed using the same ultrasound system and data acquisition procedure to investigate the effect of ultrasound frequency on the IER at5–8 MHz.Experimental results showed that the IER measured under 33-dB gain decreased from 6.65 ± 0.23 to 3.97 ± 0.10 when the lipid concentrations were increased from 0% to 30%. When 12-dB gain was used, the IER decreased from 6.21 ± 0.29 to 3.39 ± 0.07. However, whenincreasing the frequency, the IER had a mean decreasing rate of −8.67% per MHz, which was lower than those of the C1 and C2 intensities.The proposed IER may allow gain-independent measurement on tissue echogenicity.

This paper presents a new denoising method called EMD-ITF that was based on Empirical Mode Decomposition (EMD) and the Improved Thresholding Function (ITF) algorithms. EMD was applied to decompose adaptively a noisy signal into intrinsic mode functions (IMFs). Then, all the noisy IMFs were thresholded by applying the improved thresholding function to suppress noise and improve the signal to noise ratio (SNR). The method was tested on simulated and real data and the results were compared to the EMD-Based signal denoising methods using the soft thresholding. The results showed the superior performance of the new EMD-ITF denoising over the traditional approach. The performance were evaluated in terms of SNR in dB, and Mean Square Error (MSE).

Fault Diagnosis on Journal Bearing Using Empirical Mode Decomposition

A resonant frequency retrieving method for low Q-factor materials based on resonant ultrasound spectroscopy

We propose a hybrid method for forecasting the wind speed. The wind speed data is first decomposed into intrinsic mode functions (IMFs) with empirical mode decomposition. Based on the partial autocorrelation factor of the individual IMFs, adaptive methods are then employed for the prediction of IMFs. Least squares-support vector machines are employed for IMFs with weak correlation factor, and autoregressive model with Kalman filter is employed for IMFs with high correlation factor. Multistep prediction with the proposed hybrid method resulted in improved forecasting. Results with wind speed data show that the proposed method provides better forecasting compared to the existing methods.

In power distributed generation system, analysis of power quality is a major issue and hence it is essential to implement an efficient power quality system. To address and end this issue, the proposed work is mainly focused on the detection and classification of power quality disturbances or events by applying Hilbert–Huang transform (HHT) technique. HHT technique is a novel signal processing algorithm that comprises two processes. First is the empirical mode decomposition (EMD), which is an iterative process where N number of power quality signals are decomposed into intrinsic mode functions (IMFs). The second process, Hilbert transform, is applied to each IMF component. The advantage of using these two processes makes it an attractive power tool for quality event analysis. Once the IMF is obtained, it is easy to construct a time–frequency representation model. Then, the significant features are extracted from amplitude, phase and frequency instantly, which are the contour of IMFs of each power quality disturbance. For classification, adaptive neuro-fuzzy system (NFS) classifier is used. It is an intelligent system used for the combination of neural network and fuzzy logic. Power quality features are given as input to the NFS system. The experimental simulation is conducted in a MATLAB environment, and proposed HHT has higher efficiency compared to existing methods.

In power system engineering, Transmission Lines (TLs) plays a major role, an important goal of this is to transmit the generated electricity to various distribution units. Transmission lines act as a bridge between consumers and the powerhouse. In the transmission lines, the faults often occur because they are located in open space. Quick detection and recovery of transmission lines faults are necessary to maintain the normal operation of the power system. To overcome these disturbances, techniques like Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) are used in fault detection and diagnosis. DWT is applied to decompose the fault transients, because it can simultaneously extract the data, in both time and frequency domain. EMD is used to decompose the transmission line voltages into Intrinsic Mode Function (IMFs). Four types of fault signals are generated from the grid-connected power system. Transmission line faults are created using MATLAB/Simulink.

The environment around us is very rich in acoustic information, with its scope extending beyond mere speech signals. Perception of acoustic information plays a significant role in allowing human beings to comprehend sounds that they hear in their surroundings. This paper focuses on the development of feature extraction and accurate classification of variety of acoustic sounds in unstructured environments, where adverse effects such as noise, distortion are likely to dominate. This work attempts to classify ten different unstructured real-world acoustic environments using empirical mode decomposition (EMD) which considers inherent non-stationarity of acoustic signals by decomposing the signal into intrinsic mode functions (IMFs). These IMFs are used for feature extraction. This work suggests utility of composite feature set for classification and proposes an optimized, robust, best-suitable feature set for classification of the diverse acoustic environments. For the classification task, Gaussian mixture model (GMM) and k-nearest neighbor (k-NN) classifiers are used. Utilization of this optimized best-suitable feature set yields the maximum classification accuracy of 100 % with GMM classifier and an average accuracy of 95 % for k-NN (k = 1, 3, 5). Lastly, this study presents the use and comparison of various performance metrics to evaluate classification techniques used.