Detection of faults in electrical panels using deep learning method

Mlakić, Dragan; Nikolovski, Srete; Baus, Zoran

doi:10.1109/sst.2017.8188670

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…✓ In the transformer 10/0.4 kV at the transformer medium-voltage connection (transformer protection) [15]. The selection of operating level and time of operation of appropriate protection must be chosen to meet all fundamental requirements for protection operation (speed, sensitivity, reserve, selectivity) while respecting the short-term permissible and rated currents of equipment in the power grid and power plant.…”

Section: Protection Of Distribution Gridmentioning

confidence: 99%

Protection Coordination of Photovoltaic Power Plant in the Time Domain

Čolak,

Nikolovski,

Kljajić

et al. 2024

adeletters

View full text Add to dashboard Cite

The safety of workers and equipment in the power grid requires the shutdown of power plants in case of maintenance or malfunction. The shutdown relies on protective devices that must be properly coordinated to isolate only the part of the grid affected by the malfunction. Using the DIgSILENT PowerFactory software, an analysis was conducted on a model of an accurate real grid integrating a photovoltaic power plant with a capacity of 390 kW. Protection coordination testing was carried out for three-phase, two-phase, and single-phase short circuit currents at arbitrarily selected locations at medium and low voltage levels. Protection in the time domain is coordinated on lines and busbars to determine the speed and selectivity of protective devices. The analysis results indicate that adequately adjusting the three-phase short circuit at the main transformer output 110/10 kV with an impedance of 0 Ω and an allowed protection operation time of up to two seconds can be correctly addressed within 36.7 ms.

show abstract

Section: Protection Of Distribution Gridmentioning

confidence: 99%

Protection Coordination of Photovoltaic Power Plant in the Time Domain

Čolak,

Nikolovski,

Kljajić

et al. 2024

adeletters

View full text Add to dashboard Cite

show abstract

“…The harmonic source identification using artificial neural networks (ANN) method to the problem of harmonic load diagnosis has some practical issue and they are discussed in [24], [25]. ANN has an ability to study the mathematical relationship of series input and output variables which are independent or predictor variables [26], [27]. However, the ANN model suffers from overfitting of a training data set and bad performance in external test data sets [28], [29].…”

Section: Bulletin Of Electr Eng and Infmentioning

confidence: 99%

K-nearest neighbor and naïve Bayes based diagnostic analytic of harmonic source identification

et al. 2021

View full text Add to dashboard Cite

This paper proposes a comparison of machine learning (ML) algorithm known as the k-nearest neighbor (KNN) and naïve Bayes (NB) in identifying and diagnosing the harmonic sources in the power system. A single-point measurement is applied in this proposed method, and using the S-transform the measurement signals are analyzed and extracted into voltage and current parameters. The voltage and current features that estimated from time-frequency representation (TFR) of S-transform analysis are used as the input for MLs. Four significant cases of harmonic source location are considered, whereas harmonic voltage (HV) and harmonic current (HC) source type-load are used in the diagnosing process. To identify the best ML, the performance measurement of the proposed method including the accuracy, precision, specificity, sensitivity, and F-measure are calculated. The sufficiency of the proposed methodology is tested and verified on IEEE 4-bust test feeder and each ML algorithm is executed for 10 times due to prevent any overfitting result.

show abstract

“…Numerous studies have proposed various methods for three-phase inverter open circuit (OC) failure diagnostics, including model-based algorithms and signal processing-based algorithms especially timefrequency domain analysis [31], [59]- [65]. Several researchers have presented model-based methods for diagnosing faulty switches through all the study of the system model, which demonstrate excellent accuracy and strong applicability but require a precise mathematical model or additional hardware [12], [66]- [72]. Previous model-based techniques, on the other hand, are susceptible to system characteristics and have limited detection accuracy [73]- [75].…”

Section: Introductionmentioning

confidence: 99%

An analysis of voltage source inverter switches fault classification using short time Fourier transform

Manap

Nikolovski

Skamyin

et al. 2021

IJPEDS

Self Cite

View full text Add to dashboard Cite

<p>The dependability of power electronics systems, such as three-phase inverters, is critical in a variety of applications. Different types of failures that occur in an inverter circuit might affect system operation and raise the entire cost of the manufacturing process. As a result, detecting and identifying inverter problems for such devices is critical in industry. This study presents the short-time Fourier transform (STFT) for fault classification and identification in three-phase type, voltage source inverter (VSI) switches. TFR represents the signal analysis of STFT, which includes total harmonic distortion, instantaneous RMS current, RMS fundamental current, total non harmonic distortion, total waveform distortion and average current. The features of the faults are used with a rule-based classifier based on the signal parameters to categorise and detect the switch faults. The suggested method's performance is evaluated using 60 signals containing short and open circuit faults with varying characteristics for each switch in VSI. The classification results demonstrate the proposed technique is good to be implemented for VSI switches faults classification, with an accuracy classification rate of 98.3 percent.</p>

show abstract

Detection of faults in electrical panels using deep learning method

Cited by 6 publications

References 7 publications

Protection Coordination of Photovoltaic Power Plant in the Time Domain

Protection Coordination of Photovoltaic Power Plant in the Time Domain

K-nearest neighbor and naïve Bayes based diagnostic analytic of harmonic source identification

An analysis of voltage source inverter switches fault classification using short time Fourier transform

Contact Info

Product

Resources

About