Fault Classification for Transmission Lines Based on Group Sparse Representation

Shi, Shan; Zhu, Beier; Mirsaeidi, Sohrab; Dong, Xiaowen

doi:10.1109/tsg.2018.2866487

Cited by 33 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the domain of IST algorithms, advancements in reconstruction algorithms primarily stem from developments based on Orthogonal Matching Pursuit (OMP) [21]. This paper adopts the Generalized Orthogonal Matching Pursuit (GOMP) reconstruction algorithm to solve the group sparse model [22]. Initially, each column of every sub-dictionary in the group sparse dictionary D undergoes an arithmetic squaring operation with the measurement data y.…”

Section: The Reconstruction Of Disturbance Measurement Datamentioning

confidence: 99%

A Disturbance Localization Method for Power System Based on Group Sparse Representation and Entropy Weight Method

Wang,

Jiao,

Wang

et al. 2024

ENERGY

View full text Add to dashboard Cite

This paper addresses the problem of complex and challenging disturbance localization in the current power system operation environment by proposing a disturbance localization method for power systems based on group sparse representation and entropy weight method. Three different electrical quantities are selected as observations in the compressed sensing algorithm. The entropy weighting method is employed to calculate the weights of different observations based on their relative disturbance levels. Subsequently, by leveraging the topological information of the power system and pre-designing an overcomplete dictionary of disturbances based on the corresponding system parameter variations caused by disturbances, an improved Joint Generalized Orthogonal Matching Pursuit (J-GOMP) algorithm is utilized for reconstruction. The reconstructed sparse vectors are divided into three parts. If at least two parts have consistent node identifiers, the node is identified as the disturbance node. If the node identifiers in all three parts are inconsistent, further analysis is conducted considering the weights to determine the disturbance node. Simulation results based on the IEEE 39-bus system model demonstrate that the proposed method, utilizing electrical quantity information from only 8 measurement points, effectively locates disturbance positions and is applicable to various disturbance types with strong noise resistance.

show abstract

Section: The Reconstruction Of Disturbance Measurement Datamentioning

confidence: 99%

A Disturbance Localization Method for Power System Based on Group Sparse Representation and Entropy Weight Method

Wang,

Jiao,

Wang

et al. 2024

ENERGY

View full text Add to dashboard Cite

show abstract

“…The simulated fault and no‐fault data are generated from the simulation model of an IEEE 30 bus system implemented in MATLAB/SIMULINK environment 53 . The system frequency is 50 Hz 20 and the sampling frequency for buses is 2 kHz 54 . This generates a total of 40 samples (ie, 2000/50) of data from one cycle of the signal waveform.…”

Section: Studied System and Data Generationmentioning

confidence: 99%

Classification of faults in an IEEE 30 bus transmission system using fully convolutional network

Tikariha

Londhe

Bag

et al. 2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary Fault diagnosis is vital for detecting the type of fault and rapid restoration of the electric power supply. The existing machine learning‐based classification method for detecting fault shows better performance. But these methods require manual pre‐processing steps and feature engineering, which makes them unreliable and time‐consuming for the complex and multi‐bus system. In this paper, a fully automated approach based on a deep learning framework has been proposed for the multi‐classification of faults in a grid network. The deep learning framework provides a better incentive to predict the type of fault directly using raw data as input. For this intended task of fault diagnosis, a fully convolutional network is designed and implemented to provide better performance with less trainable parameters. The proposed scheme is tested on the large number of simulated data generated from an IEEE 30 bus system. The performance for fault classification is validated through 10‐fold cross‐validation and numerous performance metrics like accuracy, recall, precision, specificity, and F1 score are evaluated. The performance of the different models with parameter variation is compared to obtain better performance with optimal trainable parameters. It has also been compared with some existing methods and shows promising result for fault classification in the large or multi‐bus system.

show abstract

“…Several related sparse theories have attracted extensive attention and study. L 0 -Norm, basis pursuit denoising (BPDN), and the Least Absolute Shrinkage and Selection Operator (lasso), all of which can produce sparse effects [22][23][24]. The diagnosis of bearing fault signals based on SR is becoming more and more abundant [25,26].…”

Section: Introductionmentioning

confidence: 99%

A time-frequency sparse strategy based on optimal flux atom and scale lp approximation operator

Han¹,

Lü²,

Wang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Periodic impulse features caused by damage to rotating mechanical components are often overwhelmed by redundant components, which seriously affect the fault detection and diagnosis of equipment. Therefore, the time-frequency sparse (TFS) strategy based on optimal flux atom (OFA) and scale lp approximation operator(lp-AO) is proposed to extract periodic fault features. The OFA is determined by short-time Fourier transform (STFT) and correlation analysis of the signals. The convolutional coefficients are obtained by one-dimensional convolutional denoising based on the optimal flux atom (ODCDN-OFA). The convolution coefficients retain the main timing features of the signal. The scale lp-AO sparse model extracts the main frequency features of the convolutional coefficients in the frequency domain. The solution of the lp-AO sparse model relies on the Iterative Reweighed Least Squares (IRLS) algorithm. The effectiveness of the TFS is demonstrated by the analysis of simulated and several experimental signals. The two methods of fast spectral kurtosis (SK) and lq sparse model are used as comparisons. The TFS is demonstrated to be more effective for extracting periodic fault features.

show abstract

Fault Classification for Transmission Lines Based on Group Sparse Representation

Cited by 33 publications

References 26 publications

A Disturbance Localization Method for Power System Based on Group Sparse Representation and Entropy Weight Method

A Disturbance Localization Method for Power System Based on Group Sparse Representation and Entropy Weight Method

Classification of faults in an IEEE 30 bus transmission system using fully convolutional network

A time-frequency sparse strategy based on optimal flux atom and scale lp approximation operator

Contact Info

Product

Resources

About