A New Hybrid Protection Algorithm for Protection of Power Transformer Based on Discrete Wavelet Transform and ANFIS Inference Systems

Salama, A.M.; Abdel-Latif, K.M.; Ismail, Mohamed M.; Mousa, Sabry

doi:10.1515/ijeeps-2017-0248

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For power transformers, based on adaptive neurofuzzy inference systems and discrete wavelet transform, Salama, et al presented a hybrid algorithm for simulating the faults [20].…”

Section: Introductionmentioning

confidence: 99%

Transformer Faults Classification Based on Convolution Neural Network

A. Elmohallawy,

Yassin Hassan,

F. Abdel-Gawad

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

This paper studies the latest advances made in Deep Learning (DL) methods utilized for transformer inrush and fault currents classification. Inrush and fault currents at different operating conditions, initial flux and fault type are simulated. This paper presents a technique for the classification of power transformer faults which is based on a DL method called convolutional neural network (CNN) and compares it with traditional artificial neural network (ANN) and other techniques. The inrush and fault current signals of the transformer are simulated within MATLAB by using Fourier analyzers that provides the 2nd harmonic signal. The 2nd harmonic peak and variance statistic values of input signals of the three phases of transformer are used at different operating conditions. The resulted values are aggregated into a dataset to be used as an input for the CNN model, then training and testing the CNN model is performed. Consequently, it is obvious that the CNN algorithm achieves a better performance compared to other algorithms. This study helps with easy discrimination between normal signals and faulty signals and to determine the type of the fault to clear it easily.

show abstract

“…For power transformers, based on adaptive neurofuzzy inference systems and discrete wavelet transform, Salama, et al presented a hybrid algorithm for simulating the faults [20].…”

Section: Introductionmentioning

confidence: 99%

Transformer Faults Classification Based on Convolution Neural Network

A. Elmohallawy,

Yassin Hassan,

F. Abdel-Gawad

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…According to the research idea of multi‐feature fusion, many protection algorithms integrating data driven and AI have been published for transformer protection. At present, the differential current is still the main research object, for instance: (i) it is directly used as an input to train machine learning algorithms, such as decision tree [26, 27], random forest [28], artificial neural network (ANN) [29–33], probabilistic neural network [34–36], radial basis neural network [37], and so on; (ii) the features that are extracted from the differential current by the tools, such as wavelet transform [38–44], Clarke transform [45], principal component analysis [46], and so on, are used as the inputs of machine learning algorithms; (iii) the running states are identified through pattern recognition methods such as fuzzy theory [32, 47, 48]; (iv) according to the theory of image recognition, mathematical morphology [49, 50] is used for identifying the running states, in addition, deep learning algorithms such as convolutional neural networks (CNNs) [51, 52] have also received attention in recent years. Besides the methods mentioned above, some scholars put forward the concept of equivalent magnetisation curve [53] whose several geometric features are extracted to train an support vector machine (SVM) for the identification of running states.…”

Section: Introductionmentioning

confidence: 99%

Knowledge‐based artificial neural network for power transformer protection

Jiao

2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…ANFIS technique is a combination of two methods -the Fuzzy and Neural Networks, designed to produce a new hybrid intelligent technology. By applying the ANFIS technique, it is expected to minimize short circuit fault in power transformers, both internal and external (Salama, Abdel-Latif, Ismail & Mousa, 2018;Ge et al, 2018;Lei et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Assess the Risk Level of Power Transformer Due Short-Circuit Faults Based on Anfis

Zakri

Mustafa

Firdaus

et al. 2019

Sinergi

View full text Add to dashboard Cite

A power transformer is an electrical machine that converts electrical power at different voltage levels. Faults, occur in power transformers, inhibit electrical power distribution to the consumer. Protection, therefore, of the power transformers is essential in power systems reliability. The power system can be reliable if the protection devices work well when there is a fault. A hybrid intelligent technique, which is a combination of Artificial Neural Network (ANN) and Fuzzy known as Adaptive Neuro-Fuzzy Inference Systems (ANFIS), was used in this research. The objective of this paper is the simulation of differential relays as a protection device on power transformers using Matlab/Simulink. Performance of differential relays for power transformers protection is carried out with internal and external fault scenarios. The input data were classified into three different input for ANFIS such as internal and external 1, internal and external 2, internal, external 1, and external 2, respectively. The error results of ANFIS training for the type of fault internal and external 1 is 9.46*10-7, and types of fault internal and external 2 is 1.09*10-6 internal, external 1 and external 2 are 8.59*10-7. The results obtained from the simulation were accurate and shows that the ANFIS technique is an efficient method that gives less error and a great value. Finally, the technique can minimize faults with power transformers. Finally, to prove this method can reduce faults in the power transformer, the assess of this model has been carried out through the RMSE that has been generated which is zero.

show abstract

A New Hybrid Protection Algorithm for Protection of Power Transformer Based on Discrete Wavelet Transform and ANFIS Inference Systems

Cited by 3 publications

References 10 publications

Transformer Faults Classification Based on Convolution Neural Network

Transformer Faults Classification Based on Convolution Neural Network

Knowledge‐based artificial neural network for power transformer protection

Assess the Risk Level of Power Transformer Due Short-Circuit Faults Based on Anfis

Contact Info

Product

Resources

About