A New Methodology for Identifying Arc Fault by Sparse Representation and Neural Network

Wang, Yangkun; Zhang, Feng; Zhang, Shiwen

doi:10.1109/tim.2018.2826878

Cited by 100 publications

(53 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this comparison, it can be seen that the architecture of the proposed method based on a Kalman filter has the important advantage to detect arcing faults in the transient regime considering different maskingtype configurations (including EMI tests) on a larger number of loads (simple and combined). Also, the greatest advantage of the proposed method compared to proposed approaches [4,6,7,9,14,25] is the using of an adaptive thresholding mechanism which can avoid efficiently unwanted trips in the process of fault detection without requiring complex training tasks as are used in approaches [27][28][29]. Moreover, concerning the time response, the proposed method gives satisfactory results and exceeds the requirements defined by the standard IEC 62606 (tripping time=0.12 s for line current = 32 A).…”

Section: Case 3: Parallel Disturbing Appliancementioning

confidence: 89%

“…Statistical techniques used for the selection of static thresholds presented in [26] are not sufficient to develop robust algorithms capable of avoiding false activation on circuit breakers. Another solution is to use a neural network or an SVM [27][28][29]. However, they require long learning stages and are difficult to implement in a conventional electronic circuit board.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kalman filter and a fuzzy logic processor for series arcing fault detection in a home electrical network

Calderon-Mendoza

Schweitzer

Weber

2019

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

This paper presents a method for detecting series arcing faults in AC home electrical networks. The proposed algorithm is based on both a Kalman filter, used for identifying fault symptoms and a decision block, which confirms the presence of a series arc fault to activate a tripping signal. The current measured at one end of the power line is estimated using a model of two steady-state variables (X1 and X2). Firstly, residuals and the third order difference of state X2 are used as input parameters of a Fuzzy logic processor for detecting fault symptoms. Secondly, the fault symptoms are processed by a detection logic block, which confirms the presence of an electrical arcing fault. The algorithm is tested on a variety of loads in single or masking load configurations chosen accordingly to the requirements of the UL 1699 and IEC 62606 standards. The algorithm is also tested in the steady state or at load start (transient state). This method's performance is studied and discussed in the final part. Experimental results show that the method we propose can detect arcing faults efficiently, avoiding false tripping, whilst taking into account a high degree of diagnosis accuracy and average detection time.

show abstract

Section: Case 3: Parallel Disturbing Appliancementioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Kalman filter and a fuzzy logic processor for series arcing fault detection in a home electrical network

Calderon-Mendoza

Schweitzer

Weber

2019

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

show abstract

“…This technique has been recently used recently in the literature. Sparse representation and neural network approach were proposed in [9] to identify arc faults in distribution systems, where the learned bases resulted in a high accuracy classifier for the relevant types of arcs. In [10], sparse representations are used to denoise and compress power systems disturbances, that despite originated from a pre-defined set of basis, overperforms other techniques.…”

Section: Introductionmentioning

confidence: 99%

Vegetation High-Impedance Faults’ High-Frequency Signatures via Sparse Coding

Gomes

Ozansoy

Ulhaq

2020

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

The behavior of High-Impedance Faults (HIFs) in power distribution systems depends on multiple factors, making it a challenging disturbance to model. If enough data from real staged faults is provided, signal processing techniques can help reveal patterns from a specific type of fault. Such a task is implemented herein by employing the Shift-Invariant Sparse Coding (SISC) technique on a data set of staged vegetation high-impedance faults. The technique facilitates the uncoupling of shifted and convoluted patterns present in the recorded signals from fault tests. The deconvolution of these patterns was then individually studied to identify the possible repeating fault signatures. The work is primarily focused on the investigation of the under-discussed high-frequency faults signals, especially regarding voltage disturbances created by the fault currents. Therefore, the main contribution from this paper is the resulted evidence of consistent behavior from real vegetation HIFs at higher frequencies. These results can enhance phenomena awareness and support future methodologies dealing with these disturbances.

show abstract

“…However, the process of constructing the gray image is able to be undertaken with the loss of detailed information about the current. Sparse representation is able to directly reduce the dimension of the original signal to construct the high-dimensional feature [26] and a neural network is applied to realize the arc fault detection. However, the overlapping points of the features in the feature space make the features unable to effectively represent the characteristics of the arc faults under different load types.…”

Section: Introductionmentioning

confidence: 99%

A Novel Arc Fault Detection Method Integrated Random Forest, Improved Multi-scale Permutation Entropy and Wavelet Packet Transform

et al. 2019

View full text Add to dashboard Cite

Arc faults are one of the important causes of electric fires. In order to solve the problem of randomness, diversity, the concealment of series arc faults and to improve the detection accuracy, a novel arc fault detection method integrated random forest (RF), improved multi-scale permutation entropy (IMPE) and wavelet packet transform (WPT) are designed. Firstly, singular value decomposition (SVD) was applied to filter the current signal and then the high-dimensional fault features were constructed by extracting IMPE, the wavelet packet energy and the wavelet packet energy-entropy. Afterward, the high-dimensional fault features were employed to train the RF to realize the arc fault detection of different load types and the experimental results verify the effectiveness of the arc fault detection method designed in this paper. Finally, the comparative experiments demonstrates that the RF shows better performance in arc fault detection compared to the back-propagation neural network (BPNN) and least squares support vector machines (LSSVM), and that the experiments of transient events indicate that RF is able to effectively avoid incorrectly detecting different load types during the start operations and stop operations.

show abstract

A New Methodology for Identifying Arc Fault by Sparse Representation and Neural Network

Cited by 100 publications

References 29 publications

Kalman filter and a fuzzy logic processor for series arcing fault detection in a home electrical network

Kalman filter and a fuzzy logic processor for series arcing fault detection in a home electrical network

Vegetation High-Impedance Faults’ High-Frequency Signatures via Sparse Coding

A Novel Arc Fault Detection Method Integrated Random Forest, Improved Multi-scale Permutation Entropy and Wavelet Packet Transform

Contact Info

Product

Resources

About