Results Of Empirical Mode Decomposition Research Articles

A New Method of Tractor Engine State Identification Based on Vibration Characteristics

Based on signal decomposition, a tractor engine state recognition method is proposed to explore the degree of information recognition of vibration signals at measurement points at different distances from the engine and the degree of correlation in different directions. The accuracy of engine operating state information recognition was obtained by analyzing the vibration signals of the tractor at different measurement points. The main contents are as follows: Based on variational mode decomposition (VMD), the modal component, which includes the state information, was obtained by measuring the vibration signal of the tractor at each measurement point under different driving conditions, and the exogenous excitation of the tractor under different road conditions was simulated by changing the tire pressure. Then, the state characteristics of the modal component were quantified based on permutation entropy (PE), and the correlation coefficient was used as the evaluation index to select the entropy of the optimal modal component as the feature vector. Finally, a support vector machine and random forest classification models were trained with 4800 feature vectors under 25 working conditions, and the remaining 900 feature vectors were used to verify the classification results. Compared with the results of empirical mode decomposition (EMD), the superiority of this method was proved. A comparative study with backpropagation demonstrated the superiority of the support vector machine and random forest identification method using a small sample size. The results indicate the following: (1) the accuracy of engine condition recognition, which was measured by longitudinal vibration signals, was better than that of vertical vibration signals at different measurement points; and (2) the closer the vibration transmission distance between the measurement point and the engine, the higher the recognition accuracy of the measured signals. This study provides a reference for the condition identification of agricultural machinery in complex working environments and lays a foundation for the fault diagnosis of agricultural machinery under working conditions.

Composite fault diagnosis of gearbox based on empirical mode decomposition and improved variational mode decomposition

In order to identify the nonlinear nonstationary pitting-wear fault signal of gears in gearbox, a new method of composite fault diagnosis for gearbox is proposed, which combines empirical mode decomposition with improved variational mode decomposition. Aiming at the problem of false modes in the results of empirical mode decomposition when processing signals, the energy method is used to eliminate and update the mode components, and the correlation coefficient method is used to calculate the correlation between the updated mode components and the original signal. The components with strong correlation are selected to form the combined mode components to weaken the noise and improve the signal-to-noise ratio. Aiming at the problem that variational mode decomposition method needs to manually determine the number of mode components [Formula: see text] and the penalty factor [Formula: see text] during signal decomposition, a combination of envelope spectral entropy and waveform method is proposed to determine the optimal parameter combination. By analyzing the pitting-wear composite fault vibration signals of gears in the gearbox and the normal signals of the gearbox, the effectiveness of the proposed method is verified, and a comparative analysis with the empirical mode decomposition method is performed to highlight the superiority of the proposed method.

Short-Term Load Forecasting Based on Frequency Domain Decomposition and Deep Learning

In this paper, we focus on the accuracy improvement of short-term load forecasting, which is useful in the reasonable planning and stable operation of the system in advance. For this purpose, a short-term load forecasting model based on frequency domain decomposition and deep learning is proposed. The original load data are decomposed into four parts as the daily and weekly periodic components and the low- and high-frequency components. Long short-term memory (LSTM) neural network is applied in the forecasting for the daily periodic, weekly periodic, and low-frequency components. The combination of isolation forest (iForest) and Mallat with the LSTM method is constructed in forecasting the high-frequency part. Finally, the four parts of the forecasting results are added together. The actual load data of a Chinese city are researched. Compared with the forecasting results of empirical mode decomposition- (EMD-) LSTM, LSTM, and recurrent neural network (RNN) methods, the proposed method can effectively improve the accuracy and reduce the degree of dispersion of forecasting and actual values.

Improvement of Decomposing Results of Empirical Mode Decomposition and its Variations for Sea-level Records Analysis

ABSTRACT Lee, H.S., 2018. Improvement of decomposing results of empirical mode decomposition and its variations for sea-level records analysis. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 526–530. Coconut Creek (Florida), ISSN 0749-0208. The performance of empirical mode decomposition (EMD) and its variations such as ensemble EMD (EEMD), complete EEMD with adaptive noise (CEEMDAN) and improved CEEMDAN (impCEEMDAN) are tested using artificial signal tests. In the artificial signal test, intrinsic mode functions (IMFs) are obtained using EMD, EEMD, CEEMDAN, and impCEEMDAN and then compared to prescribed oscillations in an artificial a priori known signal. In all cases, extra and redundant modes are found due to residual noises. Furthermore, the low frequency modes are generally distorted. To overcome this problem a novel approach for reconstructing IMFs is p...

Improved Empirical Mode Decomposition Based on Harmonic Wavelet Filter

The decomposition result of empirical mode decomposition (EMD) may be incorrect if some frequency components of original signal are close to each other. To avoid illusive result and get an exact one suiting for analysis, a harmonic wavelet filtering can be used before the EMD is performed. In the course of application of harmonic wavelet filtering, data was decomposed subsection overlapped to overcome the edge effect of usual digital filter that is caused by data truncation. The experiments showed its feasibility and validity in application of real-time processing.

EMD APPROACH TO MULTICHANNEL EEG DATA — THE AMPLITUDE AND PHASE COMPONENTS CLUSTERING ANALYSIS

Human brains exhibit a possibility to control directly the intelligent computing applications in form of brain computer/machine interfacing (BCI/BMI) technologies. Neurophysiological signals and especially electroencephalogram (EEG) are the forms of brain electrical activity which can be easily captured and utilized for BCI/BMI applications. Those signals are unfortunately usually very highly contaminated by external noise caused by the presence of different devices in the environment creating electromagnetic interference. In this paper, we first decompose each of the recorded channels, in multichannel EEG recording environment, into intrinsic mode functions (IMF) which are a result of empirical mode decomposition (EMD) extended to multichannel analysis. We present novel and interesting results on human mental and cognitive states estimation based on analysis of the above-mentioned stimuli-related IMF components. The IMF components are further clustered for their spectral similarity in order to identify only those carrying responses to present stimuli to the subjects. The resulting targets only reconstruction allows us to identify when and to which stimuli intelligent application user is tuning at a time.

Application of empirical mode decomposition based energy ratio to vortex flowmeter state diagnosis

To improve the measurement performance, a method for diagnosing the state of vortex flowmeter under various flow conditions was presented. The raw sensor signal of the vortex flowmeter was adaptively decomposed into intrinsic mode functions using the empirical mode decomposition approach. Based on the empirical mode decomposition results, the energy of each intrinsic mode function was extracted, and the vortex energy ratio was proposed to analyze how the perturbation in the flow affected the measurement performance of the vortex flowmeter. The relationship between the vortex energy ratio of the signal and the flow condition was established. The results show that the vortex energy ratio is sensitive to the flow condition and ideal for the characterization of the vortex flowmeter signal. Moreover, the vortex energy ratio under normal flow condition is greater than 80%, which can be adopted as an indicator to diagnose the state of a vortex flowmeter.

Wave and Group Transformation by a Hilbert Spectrum

The Hilbert-Huang Transform (HHT) method for nonlinear and non-stationary time series analysis is applied to wave field data from the nearshore area. The frequency-time distribution of the energy, designated as a Hilbert spectrum is utilized for the examination of the sea waves and their group structure. The key feature of the HHT method is Empirical Mode Decomposition (EMD), which provides a unique basis for expansion of the data, derived from and based on the data. The necessary condition for the existence of wave grouping is determined based on the results of Empirical Mode Decomposition of the data. An attempt is made to investigate the transformation of the sea waves by examination of the decomposition components along the beach profile. The cross-shore variations of the group characteristics are studied. The Hilbert-Huang Transform method provides new insights on the wave and group cross-shore transformation.