A Differential Relay for Power Transformers Using Intelligent Tools

Segatto, Ênio Carlos; Coury, Denis Vinicius

doi:10.1109/tpwrs.2006.879268

Cited by 60 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, these methods use filters along with harmonic components to secure the relays from magnetic inrush or over-excitation situations. The filtering procedure can delay the protection process [7,8]. Besides this, if harmonics are present in the unsaturated CT secondary signal then the detector output may be high even though there is no saturation.…”

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

et al. 2017

View full text Add to dashboard Cite

Current transformer (CT) saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL) methods have brought a subversive revolution in the field of artificial intelligence (AI). This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs) to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

show abstract

Section: Motivationmentioning

confidence: 99%

“…Here, β is the weight of sparsity term and S 2 is the number of hidden units. Moreover, the average activation of the hidden unit j in the AE is defined in Equation (7). Herê ρ j is equal to ρ which is known as sparsity parameter.…”

Section: Sparsity Of the Autoencoder (Ae)mentioning

confidence: 99%

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In general, the transformation is realized using digital circuits, where measured quantities are sampled and converted to discrete signals. The sampling of the quantities results in converting continuous frequencies of the quantities into discrete frequencies based on the sampling frequency as in the following formula [21]: (10) where is a discrete frequency, is a continuous frequency, and is the sampling frequency. The conversion of the discretized quantities into their axis components implies relocating the discrete frequencies into a low half-band and a high halfband as:…”

Section: B Wpt-based Ddcmentioning

confidence: 99%

“…The extraction of the 1st, 2nd, and 5th harmonic components can be achieved using passive filters, Fourier transforms, sine-cosine correlations, rectangular transforms, Haar functions, Walsh functions, Kalman filters, least-square algorithms, etc. [1]- [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Development of a $d$–$q$ Axis WPT-Based Digital Protection for Power Transformers

Saleh

Aktaibi

Ahshan

et al. 2012

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper presents the analysis and development of a new digital differential protection for three phase (3 ) power transformers. The proposed digital protection is based on extracting high frequency sub-band contents present in the axis components of the differential currents in order to identify internal faults. The desired high frequency sub-band contents are extracted using a single-stage wavelet packet transform (WPT), which offers parameterizing the energy in the high frequency sub-band contents using a finite number of coefficients. The WPT coefficients contain information that offer accurate, fast, and reliable detection and classification of transient disturbances, including magnetizing inrush and internal fault currents that may be experienced by 3 power transformers. The WPT-based digital differential protection is implemented for off-line performance evaluation using differential currents collected from a 5 kVA, 3 , laboratory power transformer. Off-line test results demonstrate accurate, fast, and reliable detection, classification, and response to different types of fault and non-fault currents. These encouraging performances of the WPT-based digital differential protection are obtained with simple implementation, reduced computational burdens, and small memory requirements.Index Terms-Digital differential protection, digital filters, internal fault currents, magnetizing inrush current, synchronous rotating reference frame ( axis), three phase power transformers, wavelet analysis. NOMENCLATURE-point circular convolution operation. Continuous frequency.Discrete frequency. Scaling function.Wavelet function associated with . Set of real numbers. Inception angle. Set of integer numbers. Approximation signal at scale and shift .

show abstract

Classification and Forecasting

2009

Spotlight on Modern Transformer Design

View full text Add to dashboard Cite

A Differential Relay for Power Transformers Using Intelligent Tools

Cited by 60 publications

References 18 publications

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

The Development of a $d$–$q$ Axis WPT-Based Digital Protection for Power Transformers

Classification and Forecasting

Contact Info

Product

Resources

About