Time-Frequency Analysis Based on Improved Variational Mode Decomposition and Teager Energy Operator for Rotor System Fault Diagnosis

Liu, Shangkun; Tang, Guiji; Wang, Xiaolong; He, Yu‐Ling

doi:10.1155/2016/1713046

Cited by 26 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Case 1, we obtained the actual FBG noisy signal by adding different SNR levels of white Gaussian noise to the experimental FBG signal. To evaluate the de-noising effect, quantitative evaluating indexes, such as the mean absolute error (MAE), the root-mean-square error (RMSE), and the SNR, are proposed here to assess the de-noising methods [26,27]. Additionally, the cross-correlation coefficient is proposed to estimate the correlation between the noisy signal and the denoising signal.…”

Section: Case 1: Applying Vmd To Mixed Fbg Noisy Signalsmentioning

confidence: 99%

Denoising of the Fiber Bragg Grating Deformation Spectrum Signal Using Variational Mode Decomposition Combined with Wavelet Thresholding

Zhang

Zhao

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Damage detection using an FBG sensor is a critical process for an assessment of any inspection technology classified as structural health monitoring (SHM). FBG signals containing noise in experiments are developed to detect flaws. In this paper, we propose a novel signal denoising method that combines variational mode decomposition (VMD) and changed thresholding wavelets to denoise experimental and mixed signals. VMD is a recently introduced adaptive signal decomposition algorithm. Compared with traditional empirical mode decomposition (EMD), and it is well founded theoretically and more robust to noise samples. First, input signals were broken down into a given number of K band-limited intrinsic mode functions (BLIMFs) by VMD. For the purpose of avoiding the impact of overbinning or underbinning on VMD denoising, the mixed signals, which were obtained by adding different signal/noise ratio (SNR) noises to the experimental signals, were designed to select the best decomposition number K and data-fidelity constraint parameter α. After that, the realistic experimental signals were processed using four denoising algorithms to evaluate denoising performance. The results show that, upon adding additional noisy signals and realistic signals, the proposed algorithm delivers excellent performance over the EMD-based denoising method and discrete wavelet transform filtering.

show abstract

Section: Case 1: Applying Vmd To Mixed Fbg Noisy Signalsmentioning

confidence: 99%

Denoising of the Fiber Bragg Grating Deformation Spectrum Signal Using Variational Mode Decomposition Combined with Wavelet Thresholding

Zhang

Zhao

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Variational mode decomposition method (VMD) non-recursively decomposes a multi-component signal f(t) into various band-limited monocomponent signals or intrinsic mode functions uk(t) using calculus of variation [8]. Each mode is regarded as an amplitude-modulated and frequency-modulated (AM-FM) signal and is assumed to have compact frequency support around a central frequency ωk [9]. VMD tries to find out these central frequencies and intrinsic mode functions centered on those frequencies concurrently using an optimization methodology called alternate direction method of multipliers (ADMM).…”

Section: Variational Mode Decompositionmentioning

confidence: 99%

Land Cover Classification Based on Modis Imagery Data Using Artificial Neural Networks

Stepchenko

2017

ETR

View full text Add to dashboard Cite

Remote sensing has been widely used to obtain land cover information using automated classification. Land cover is a measure of what is overlaying the surface of the earth. Accurate mapping of land cover on a regional scale is useful in such fields as precision agriculture or forest management and is one of the most important applications in remote sensing. In this study, multispectral MODIS Terra NDVI images and an artificial neural network (ANN) were used in land cover classification. Artificial neural network is a computing tool that is designed to simulate the way the human brain analyzes and process information. Artificial neural networks are one of the commonly applied machine learning algorithm, and they have become popular in the analysis of remotely sensed data, particularly in classification or feature extraction from image data more accurately than conventional method. This paper focuses on an automated classification system based on a pattern recognition neural network. Variational mode decomposition method is used asan image data pre-processing tool in this classification system. The result of this study will be land cover map.

show abstract

“…The main method uses vibration sensors which acquire the vibration signal of wind turbine, utilize some methods with strong applicability for feature extraction, and then use fault diagnosis methods to diagnose the fault by utilizing fault information extracted for wind turbine. The methods for signal processing include wavelet transform (WT) [10,11], Hilbert-Huang transform, empirical mode decomposition (EMD) [12,13], and variational mode decomposition (VMD) [14,15]. For instance, Gao et al [16] utilize load mean decomposition (LMD) decomposing the vibration signal into multiple product functions.…”

Section: Introductionmentioning

confidence: 99%

Research on Multidomain Fault Diagnosis of Large Wind Turbines under Complex Environment

Jia

Dang

et al. 2018

Complexity

View full text Add to dashboard Cite

Under the complicated environment of large wind turbines, the vibration signal of a wind turbine has the characteristics of coupling and nonlinearity. The traditional feature extraction method for the signal is hard to accurately extract fault information, and there is a serious problem of information redundancy in fault diagnosis. Therefore, this paper proposed a multidomain feature fault diagnosis method based on complex empirical mode decomposition (CEMD) and random forest theory (RF). Firstly, this paper proposes a novel method of complex empirical mode decomposition by using the correlation information between two-dimensional signals and utilizing the idea of ensemble empirical mode decomposition (EEMD) by adding white noise to suppress the problem mode mixing in empirical mode decomposition (EMD). Secondly, the collected vibration signals are decomposed into IMFs by CEMD. Then, calculate 11 time domain characteristic parameters and 13 frequency domain characteristic parameters of the vibration signal, and calculate the energy and energy entropy of each IMF components. Make all the characteristic parameters as the multidomain feature vectors of wind turbines. Finally, the redundant feature vectors are eliminated by the importance of each feature vector which has been calculated, and the feature vectors selected are input to the random forest classifier to achieve the fault diagnosis of large wind turbines. Simulation and experimental results show that this method can effectively extract the fault feature of the signal and achieve the fault diagnosis of wind turbines, which has a higher accuracy of fault diagnosis than the traditional classification methods.

show abstract

Time-Frequency Analysis Based on Improved Variational Mode Decomposition and Teager Energy Operator for Rotor System Fault Diagnosis

Cited by 26 publications

References 22 publications

Denoising of the Fiber Bragg Grating Deformation Spectrum Signal Using Variational Mode Decomposition Combined with Wavelet Thresholding

Denoising of the Fiber Bragg Grating Deformation Spectrum Signal Using Variational Mode Decomposition Combined with Wavelet Thresholding

Land Cover Classification Based on Modis Imagery Data Using Artificial Neural Networks

Research on Multidomain Fault Diagnosis of Large Wind Turbines under Complex Environment

Contact Info

Product

Resources

About