scholarly journals STUDI KOORDINASI KERJA RELE DIFERENSIAL DAN RELE RESTRICTED EARTH FAULT SETELAH UPRATING PADA TRANSFORMATOR II DI GI KAPAL

2018 ◽  
Vol 5 (1) ◽  
pp. 49
Author(s):  
I Made Dwi Cahyadi Jaya ◽  
I Gede Dyana Arjana ◽  
A.A Gede Maharta Pemayun
Keyword(s):  
Calculation Method ◽  
Calculation Result ◽  
Power Transformer ◽  
Fault Current ◽  
Earth Fault ◽  
Sensitivity Setting ◽  
Transformer Winding

The differential relay on the power transformer II in the Kapal Substation has a sensitivity setting of 30% to the nominal current of winding. Fault current that occurs below setting is not detected because the fault current has not reached the set limit. To overcome the fault current it is equipped with REF relay that has sensitivity below 30%. The analysis was performed by calculation method according to the relay setting manual. The results of sensitivity setting of REF relay is 382.75 A or fault point at 22.09% of the transformer winding, while the differential relay is 519.6 A or fault point at 30% of the transformer winding. The calculation result shows that the first to work is the REF relay than the differential relay. So the fault on the transformer winding is overcome by the REF relay.

scholarly journals Prediction of Stress in Power Transformer Winding Conductors Using Artificial Neural Networks: Hyperparameter Analysis

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4242
Author(s):  
Fausto Valencia ◽  
Hugo Arcos ◽  
Franklin Quilumba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Power Transformer ◽  
Network Models ◽  
Activation Function ◽  
Neural Network Models ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Femm Software

The purpose of this research is the evaluation of artificial neural network models in the prediction of stresses in a 400 MVA power transformer winding conductor caused by the circulation of fault currents. The models were compared considering the training, validation, and test data errors’ behavior. Different combinations of hyperparameters were analyzed based on the variation of architectures, optimizers, and activation functions. The data for the process was created from finite element simulations performed in the FEMM software. The design of the Artificial Neural Network was performed using the Keras framework. As a result, a model with one hidden layer was the best suited architecture for the problem at hand, with the optimizer Adam and the activation function ReLU. The final Artificial Neural Network model predictions were compared with the Finite Element Method results, showing good agreement but with a much shorter solution time.

Determination of Damping Factors Based on the Measured Frequency Responses of Power Transformer Windings. Part 2. Analysis of Measurement Results

2021 ◽  
Vol 2 (2) ◽  
pp. 22-28
Author(s):  
Vasily S. LARIN ◽  
◽  
Daniil A. MATVEEV ◽  
Keyword(s):  
Active Component ◽  
Power Transformer ◽  
Neutral Current ◽  
Response Analysis ◽  
Reactive Component ◽  
Input Admittance ◽  
Equivalent Scheme ◽  
Frequency Responses ◽  
Measurement Results ◽  
Transformer Winding

In the first part of the article, based on the results of theoretical studies performed for a simplified transformer winding equivalent scheme, it was shown that the damping factors can be estimated from the width of the resonant peaks of the frequency responses of the module and the reactive component of the voltage at the midpoint of the equivalent scheme, as well as the active component of the input admittance and neutral current of the considered resonant scheme. In this part of the article, the practical possibility of applying the obtained theoretical relations between the damping factors and the width of resonant peaks in relation to the frequency responses of power transformer windings is considered. The results of calculations of the damping factors at the two power transformers made by using the fitting of the free component of transient voltage and by determining the width of the resonance peaks of the active component of winding neutral current and the voltage transfer function, corresponding to intermediate points of the winding. It is shown that the evaluation of the values of the winding damping factors can be performed as a byproduct of transformer condition assessment by frequency response analysis (FRA).

Sign in / Sign up

Export Citation Format

Share Document