Harmonic separation from grid voltage using ensemble empirical-mode decomposition and independent component analysis

Cai, Kewei; Wang, Zhiqiang; Li, Guofeng; He, Di; Song, Jianwei

doi:10.1002/etep.2405

Cited by 16 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when the vibration signal is affected by strong noise, the end effect and the false component still exist in the LMD, thus a certain approach is also necessary to extract the signal sensitive information from each component. For this purpose, the independent component analysis (ICA) [21]- [23] can be employed as a superior method to extract the intrinsic component in the aliased signal affected by strong noise, and separate different source signals from the aliased signal. However, as the second analysis of signal features based upon LMD, the ICA algorithm requires that the number of observation dimensions be greater than that of the source signals, which might cause the underdetermined problem for the case of insufficient observation dimensions.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Discrimination in Terms of LMD and ICA With Combined Features in The Fiber-Optic Perimeter System

Zhang

et al. 2020

IEEE Photonics J.

View full text Add to dashboard Cite

For improving the performance of intrusion discrimination in the dual Mach-zehnder interferometric (DMZI) perimeter system, we propose a novel method based upon local mean decomposition (LMD), independent component analysis (ICA) and features combination. By the LMD-ICA, the original signal is processed to construct a virtual noise, thereby obtaining the sensitive information of the signal. With multiple features from the sensitive information, the type of intrusions can be discriminated by the method of serial feature fusion (SFF). The experiments are performed with real data for the case of the single-vibration and the single-vibration under the rain interference. The results demonstrate that the proposed method is superior to the traditional discrimination one, with an average recognition rate of over 96%.

show abstract

Section: Introductionmentioning

confidence: 99%

Intrusion Discrimination in Terms of LMD and ICA With Combined Features in The Fiber-Optic Perimeter System

Zhang

et al. 2020

IEEE Photonics J.

View full text Add to dashboard Cite

show abstract

“…The conventional methods of PQD recognition and classification contain two steps: feature extraction and classification. The feature extraction methods are mostly based on signal processing techniques, such as Fourier transform (FT) [8], short time Fourier transform (STFT) [9,10], wavelet transform (WT) [11][12][13], S-transform (ST) [14,15], empirical mode decomposition (EMD) [16][17][18], independent component analysis (ICA) [19], and variational mode decomposition (VMD) [20][21][22]. These methods are used to extract features from different types of PQDs.…”

Section: Introductionmentioning

confidence: 99%

Classifying Power Quality Disturbances Based on Phase Space Reconstruction and a Convolutional Neural Network

Cai

Cao

et al. 2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

This paper presents a hybrid approach combining phase space reconstruction (PSR) with a convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a PSR technique is developed to transform a 1D voltage disturbance signal into a 2D image file. Then, a CNN model is developed for the image classification. The feature maps are extracted automatically from the image file and different patterns are derived from variables in CNN. A set of synthetic signals, as well as operational measurements, are used to validate the proposed method. Moreover, the test results are also compared with existing methods, including empirical mode decomposition (EMD) with balanced neural tree (BNT), S-transform (ST) with neural network (NN) and decision tree (DT), hybrid ST with DT, adaptive linear neuron (ADALINE) with feedforward neural network (FFNN), and variational mode decomposition (VMD) with deep stochastic configuration network (DSCN). Based on deep learning algorithms, the proposed method is capable of providing more accurate results without any human intervention for PQDs. It also enables the planning of PQ remedy actions.

show abstract

“…An improved algorithm named ensemble empirical mode decomposition (EEMD) is proposed to deal with the disadvantage of EMD. It is worth mentioning that EEMD can only limit modal aliasing to a certain extent and cannot solve the problem fundamentally [15]. The variational mode decomposition (VMD) explored by Dragomiretskiy is a non-recursive way to decompose signals, which completely solves the drawbacks of EMD and EEMD [16].…”

Section: Introductionmentioning

confidence: 99%

A Rapid Accurate Recognition System for Radar Emitter Signals

et al. 2019

View full text Add to dashboard Cite

Radar signal recognition is an indispensable part of an electronic countermeasure system. In order to solve the problem that the current techniques have, which is a low recognition rate and a slow recognition speed for radar signals, a rapid accurate recognition system is proposed, especially for when multiple signals arrive at the receiver. The proposed system can recognize eight types of radar signals while separating signals: binary phase shift keying (BPSK), linear frequency modulation (LFM), Costas, Frank code, and P1–P4 codes. Regression variational mode decomposition (RVMD) is explored to separate the received signals, which saves time for parameter optimization of variational mode decomposition (VMD). Furthermore, signal separation and a noise removal technique based on VMD and the first component recognition technique based on a deep belief network (DBN) are proposed. In addition, in order to overcome the loss of the secondary component caused by signal separation, a fusion network is explored to increase the recognition rate of the secondary component in a short time. The simulation results show that the recognition system achieves an overall recognition rate of 99.5% and 94% at a signal-to-noise ratio (SNR) of 0 dB when receiving single signals and double signals, while spending 0.8 s and 2.23 s, respectively. The proposed system can also be used to recognize medical and mechanical signals.

show abstract

Harmonic separation from grid voltage using ensemble empirical-mode decomposition and independent component analysis

Cited by 16 publications

References 17 publications

Intrusion Discrimination in Terms of LMD and ICA With Combined Features in The Fiber-Optic Perimeter System

Intrusion Discrimination in Terms of LMD and ICA With Combined Features in The Fiber-Optic Perimeter System

Classifying Power Quality Disturbances Based on Phase Space Reconstruction and a Convolutional Neural Network

A Rapid Accurate Recognition System for Radar Emitter Signals

Contact Info

Product

Resources

About