A New Approach for Classification and Characterization of Voltage Dips and Swells Using 3-D Polarization Ellipse Parameters

Alam, M. R.; Muttaqi, Kashem M.; Bouzerdoum, A.

doi:10.1109/tpwrd.2014.2361624

Cited by 33 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main motivation of this work is to exploit deep learning for automatic extraction of dip features instead of using conventional methods that extract hand-crafted features using 'human experts' knowledge. It has been shown before that SPM domain dip classification is more robust than directly using the waveform or RMS voltage versus time [27][33]- [35]. We therefore propose to employ deep learning in the SPM domain.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…However, only rms voltages are used, so that information about individual phasors is lost. The methods proposed in [27], [33]- [35] use ellipse parameters for voltage dip classification. The ellipse is corresponding to either space phasor model or the polarization ellipse, in both cases calculated from the three phase-to-neutral voltages.…”

Section: A Voltage Dip Classificationmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification

Bagheri

Bollen

et al. 2018

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper proposes a novel method for voltage dip classification using deep convolutional neural networks. The main contributions of this paper include: (a) to propose a new effective deep convolutional neural network architecture for automatically learning voltage dip features, rather than extracting hand-crafted features; (b) to employ the deep learning in an effective twodimensional transform domain, under space-phasor model (SPM), for efficient learning of dip features; (c) to characterize voltage dips by two-dimensional SPM-based deep learning, which leads to voltage dip features independent of the duration and sampling frequency of dip recordings; (d) to develop robust automaticallyextracted features that are insensitive to training and test datasets measured from different countries/regions. Experiments were conducted on datasets containing about 6000 measured voltage dips spread over seven classes measured from several different countries. Results have shown good performance of the proposed method: average classification rate is about 97% and false alarm rate is about 0.50%. The test results from the proposed method are compared with the results from two existing dip classification methods. The proposed method is shown to outperform these existing methods.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: A Voltage Dip Classificationmentioning

confidence: 99%

A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification

Bagheri

Bollen

et al. 2018

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

show abstract

“…Besides the RMS, a polarized ellipse was introduced in [15] to characterise the voltage dip trajectory, and five ellipse parameters are used to classify and characterise voltage dips and swells within a one-cycle window length. As an improvement of the technique proposed in [15], the voltage space vector and least squares are used to transform the dip time series into two-dimensional polarization ellipses. The features extracted by the polarization ellipses are then used to classify the dips [16].…”

Section: Introductionmentioning

confidence: 99%

“…The features extracted by the polarization ellipses are then used to classify the dips [16]. Although these methods have obtained good performance, they require human expert knowledge [9,[11][12][13][14], feature extraction techniques [10,11], and setting of several threshold parameters [15,16]. This will lead to a complicated classification algorithm, affecting the generalization ability of the classification algorithm.…”

Section: Introductionmentioning

confidence: 99%

Identification Method for Voltage Sags Based on K-means-Singular Value Decomposition and Least Squares Support Vector Machine

et al. 2019

View full text Add to dashboard Cite

Voltage sag is one of the most serious problems in power quality. The occurrence of voltage sag will lead to a huge loss in the social economy and have a serious effect on people’s daily life. The identification of sag types is the basis for solving the problem and ensuring the safe grid operation. Therefore, with the measured data uploaded by the sag monitoring system, this paper proposes a sag type identification algorithm based on K-means-Singular Value Decomposition (K-SVD) and Least Squares Support Vector Machine (LS-SVM). Firstly; each phase of the sag sample RMS data is sparsely coded by the K-SVD algorithm and the sparse coding information of each phase data is used as the feature matrix of the sag sample. Then the LS-SVM classifier is used to identify the sag type. This method not only works without any dependence on the sag data feature extraction by artificial ways, but can also judge the short-circuit fault phase, providing more effective information for the repair of grid faults. Finally, based on a comparison with existing methods, the accuracy advantages of the proposed algorithm with be presented.

show abstract

“…Therefore, powerelectronics equipment, whose firing instants are triggered by the phase-angle information, may have adverse impact [4], [13][14]. To this end, several methods are reported in various research works for classification and characterisation of voltage dips [15][16][17][18][19][20][21].In [22], fault-types and fault-locations, which trigger voltage sags and swells, are investigated by capturing fault records. However, this paper proposes an analytical approach for assessment of voltage sags caused by balanced as well as unbalanced faults.…”

Section: Introductionmentioning

confidence: 99%

Analytical expressions for characterising voltage dips and phase‐angle jumps in electricity networks

Begum

Alam

Muttaqi

2018

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Voltage dips/sags are one of the major concerns for electricity consumers as well as utility service providers. Therefore, the characterisation of voltage dips/sags is required. This study presents a set of mathematical expressions for characterising different types of voltage dips/sags and their associated phase-angle jumps, which are typically found due to faults and/or disturbances in electricity networks. The expressions are derived analytically from the model of the power network containing generators, transmission and/or distribution lines, transformers etc. Four types of voltage dips, namely, A, B, E, and G, which are associated with four major types of faults including balanced three-phase faults, single line-toground, double lineto-ground, and line-to-line faults, are considered to derive the analytical expressions. Dynamic simulation results, using a test distribution system, approve the validity as well as the accuracy of the developed expressions. The influence of fault-types and fault-locations is investigated from the mathematical expressions; further, validation is conducted through a simulation study. The analytical expressions, presented in this study, are a valuable tool in the planning stage since the expressions can be employed to characterise during-fault voltage dips at different buses in electricity network without conducting a large number of repeated dynamic simulations.

show abstract

A New Approach for Classification and Characterization of Voltage Dips and Swells Using 3-D Polarization Ellipse Parameters

Cited by 33 publications

References 10 publications

A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification

A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification

Identification Method for Voltage Sags Based on K-means-Singular Value Decomposition and Least Squares Support Vector Machine

Analytical expressions for characterising voltage dips and phase‐angle jumps in electricity networks

Contact Info

Product

Resources

About