scholarly journals Identification of Power Transformer Currents by Using Random Forest and Boosting Techniques

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Tamer Khatib ◽  
Gazi Arar
Keyword(s):  
Expert System ◽  
Random Forest ◽  
Power Transformer ◽  
Confusion Matrix ◽  
The Other ◽  
Differential Protection ◽  
Learning Machines ◽  
Internal Fault ◽  
Component Importance ◽  
Importance Analysis

In this research, a differential protection technique for a power transformer is proposed by using random forest and boosting learning machines. The proposed learning machines aim to provide a protection expert system that distinguishes between different transformer status which are normal, inrush, overexcitation, CT saturation, or internal fault. Data for 20 different transformers with 5 operating cases are used in this research. The utilized random forest and boosting techniques are trained using these data. Meanwhile, the proposed models are validated by other measures such as out-of-bag error and confusion matrix. In addition, variable importance analysis that shows signal’s component importance inside a transformer at different instances is provided. According to the result, the proposed random forest model successfully identifies all of the current cases (100% accuracy for the conducted experiment). Meanwhile, it is found that it is less accurate as a conditional monitoring element with accuracy in the range of 97%–98%. On the other hand, the proposed boosting model identifies all of the currents for both cases (100% accuracy for the conducted experiment). In addition to that, a comparison is conducted between the proposed models and other AI-based models. Based on this comparison, the proposed boosting model is the simplest and the most accurate model as compared to other models.

A New Differential Relay Framework for Power Transformer

2014 ◽  
Vol 492 ◽  
pp. 426-430
Author(s):  
Rachid Bouderbala ◽  
Hamid Bentarzi
Keyword(s):  
Power Transformer ◽  
Circuit Breaker ◽  
Differential Protection ◽  
Test Results ◽  
Transient Currents ◽  
Fault Currents ◽  
Internal Fault ◽  
Time Signals ◽  
Data Acquisition Card ◽  
Frame Work

A differential relay that is very sensitive relay operating even at its limits may be used for protecting a power transformer. However, this characteristic may lead to unnecessary tripping due to transient currents. In order to avoid this unnecessary tripping, estimated harmonics of these currents may be required which need great computation efforts. In this paper, a new frame work is proposed using PC interfaced with a data acquisition card AD622, which acquires real-time signals of the currents, process them numerically in the computer and outputs tripping signal to the circuit breaker. All algorithms of differential protection function and blocking techniques have been implemented using the Simulink/Matlab. To validate the present work, the performance of developed relay is tested by signals generated by Simulink/MATLAB simulator under different conditions. The test results show that this proposed scheme provides good discrimination between the transient currents and the internal fault currents.

scholarly journals The study of power transformer differential protection’s operation in the internal fault conditions

2021 ◽  
Vol 288 ◽  
pp. 01096
Author(s):  
Ilya Litvinov ◽  
Aleksandra Naumova ◽  
Vasiliy Titov ◽  
Andrey Trofimov ◽  
Elena Gracheva
Keyword(s):  
Power System ◽  
High Speed ◽  
Power Transformer ◽  
Short Circuit ◽  
Differential Protection ◽  
Current Transformers ◽  
Secondary Currents ◽  
A Value ◽  
Internal Fault ◽  
Internal Short Circuit

Special attention is paid to high-speed relay protections’ operation in transient modes due to a number of major failure events that have occurred over the past 10 years in the power system of the Russian Federation. Operation of power transformer’s differential protection in case of internal short circuit is studied in this research. False blocking of protection is possible in such mode due to saturation of current transformers. A value of blocking time may exceed the maximum permissible short-circuit disconnection time under conditions of maintaining the dynamic stability of the power system. Primary and secondary currents in transient modes are obtained by simulation of short circuits. Windings of the modeled current transformers are connected in a star to a null wire. RMS values are calculated using a mathematical model of the Fourier filter. The current transformers were checked according to the methods declared in PNST 283-2018 and GOST R 58669-2019. The analysis carried out in this work allows to estimate possibility of long-term blocking of the differential protection of a power transformer in case of internal short circuit, especially in case of significant value of time constants.

scholarly journals Design and Evaluation of a DSP Based Differential Relay of Power Transformer

2021 ◽  
Vol 1 (1) ◽  
pp. 69-78
Author(s):  
Abdelkader ABDELMOUMENE ◽  
Rachid BOUDERBALA ◽  
Hamid BENTARZI
Keyword(s):  
Harmonic Analysis ◽  
Power Transformer ◽  
Inrush Current ◽  
Differential Protection ◽  
Challenging Problem ◽  
Good Discrimination ◽  
Internal Fault ◽  
Magnetizing Current

The problem of mal operation of differential protection of power transformer due to the inrush magnetizing current has long considered as a challenging problem. Several types of protection relays have been used to solve the issue (basic relay, percentage relay, multi slop ….). Each of them has its advantage and its limits. In this paper, a Digital differential relay has been developed and simulated. The logic used to distinguish between the inrush current and the internal fault is based on the theory of harmonic analysis. The behavior of the presented relay has been simulated versus various situations (inrush current, internal fault and external fault). The obtained results show that the proposed algorithm provides a good discrimination and a fast action.

scholarly journals Expert System for Early Diagnosis of Heart Disease Using the Random Forest Method

2019 ◽  
Vol 3 (1) ◽  
pp. 15
Author(s):  
Yogi Prawira Putra ◽  
Duman Care Khrisne ◽  
I Made Arsa Suyadnya
Keyword(s):  
Coronary Heart Disease ◽  
Heart Disease ◽  
Expert System ◽  
Random Forest ◽  
Early Diagnosis ◽  
Programming Language ◽  
Confusion Matrix ◽  
Training Data ◽  
Random Forest Method ◽  
Initial Symptoms

In Indonesia, coronary heart disease continues to grow. However, the efforts to prevention it can still be done by diagnosing the initial symptoms caused by using an expert system. This study was designed to build an expert system application to diagnose early coronary disease by random forest methods. The application interface was built using the PHP programming language using framework bootstrap, and uses the python programming language to build a random forest. To make an early diagnosis of coronary heart disease, a decision tree was built by training data from the UCI Dataset Machine Learning Repository using the random forest method. Followed by patient classification data that has been collected through 13 questions to get the diagnosis. The diagnosis results were normal, stadium 1, stadium 2, stadium 3 and stadium 4. Based on the tests that had been carried out, the application was able to provide results in accordance with the sample data collected using a confusion matrix resulting in an accuracy of 92.25% +/- 0.62 with 70% precision, remember 46%, which obtained a score of f0,5 72%.

Differential Protection Enhancement for Power Transformer

2021 ◽  
pp. 322-346
Author(s):  
Hamid Bentarzi ◽  
Rachid Bouderballa
Keyword(s):  
Power Transformer ◽  
Second Harmonic ◽  
Inrush Current ◽  
Differential Protection ◽  
Smart Power ◽  
The Third ◽  
Internal Fault ◽  
Harmonic Components ◽  
Magnetization Condition ◽  
Advanced Computer

A power transformer is protected against internal faults using a differential protection which is sensitive and a fast. However, during transformer magnetization (inrush current or over-excitation), the differential relay may operate unnecessarily. This phenomenon appears only when a transformer is first energized or after clearing external fault. During periodic magnetization condition due to over-excitation, the third and fifth harmonic components are largely noticed; however, during the normal apperiodic inrush conditions, the second harmonic is relatively high. In the conventional techniques, these harmonic components have been used to block differential protection to operate. However, in smart power transformer, these harmonic components are small even during the transformer magnetization; they cannot be used as block protection functions. The differential protection security has to be improved so that it can distinguish between differential current produced by magnetization and that produced by internal fault using the most advanced computer with most improved DSP algorithms.

Components Importance Analysis Fault Tree of Power Transformer of Gi Simangkuk Switchyard in Indonesia

2013 ◽  
Vol 694-697 ◽  
pp. 907-910 ◽  
Author(s):  
Josep Franklin Sihite ◽  
Takehisa Kohda
Keyword(s):  
System Reliability ◽  
Power Transformer ◽  
Fault Tree ◽  
Importance Measure ◽  
Component Importance ◽  
Safety Improvement ◽  
System Components ◽  
Importance Analysis

The purpose of this paper is to study the importance measures of power transformer system components. Importance measures analysis is a key part of the system reliability quantification process which are most effective towards safety improvement. This paper presented an application and results of the importance measures analysis of a power transformer system of GI Simangkuk switchyard in Indonesia by using Birnbaum importace measures, critically importance measure, and Fussel-Vessely importance measures. These method present the rank of the component importance measures quantitavily according to their contribution to system reliability and safety.

Nglyc: A Random Forest Method for Prediction of N-Glycosylation Sites in Eukaryotic Protein Sequence

2020 ◽  
Vol 27 (3) ◽  
pp. 178-186 ◽  
Author(s):  
Ganesan Pugalenthi ◽  
Varadharaju Nithya ◽  
Kuo-Chen Chou ◽  
Govindaraju Archunan
Keyword(s):  
Random Forest ◽  
Protein Sequence ◽  
Glycosylation Site ◽  
Computational Method ◽  
The Other ◽  
Eukaryotic Protein ◽  
Random Forest Method ◽  
Glycosylation Sites ◽  
Human And Mouse ◽  
Better Than

Background: N-Glycosylation is one of the most important post-translational mechanisms in eukaryotes. N-glycosylation predominantly occurs in N-X-[S/T] sequon where X is any amino acid other than proline. However, not all N-X-[S/T] sequons in proteins are glycosylated. Therefore, accurate prediction of N-glycosylation sites is essential to understand Nglycosylation mechanism. Objective: In this article, our motivation is to develop a computational method to predict Nglycosylation sites in eukaryotic protein sequences. Methods: In this article, we report a random forest method, Nglyc, to predict N-glycosylation site from protein sequence, using 315 sequence features. The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites. Nglyc prediction was compared with NetNGlyc, EnsembleGly and GPP methods. Further, the performance of Nglyc was evaluated using human and mouse N-glycosylation sites. Results: Nglyc method achieved an overall training accuracy of 0.8033 with all 315 features. Performance comparison with NetNGlyc, EnsembleGly and GPP methods shows that Nglyc performs better than the other methods with high sensitivity and specificity rate. Conclusion: Our method achieved an overall accuracy of 0.8248 with 0.8305 sensitivity and 0.8182 specificity. Comparison study shows that our method performs better than the other methods. Applicability and success of our method was further evaluated using human and mouse N-glycosylation sites. Nglyc method is freely available at https://github.com/bioinformaticsML/ Ngly.

A power transformer differential protection based onsupport vector machine and wavelet transform

2021 ◽  
Vol 197 ◽  
pp. 107297
Author(s):  
Lucas D. Simões ◽  
Hagi J.D. Costa ◽  
Matheus N.O. Aires ◽  
Rodrigo P. Medeiros ◽  
Flavio B. Costa ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Power Transformer ◽  
Differential Protection ◽  
Transformer Differential Protection
Sign in / Sign up

Export Citation Format

Share Document