TL–LED<sup>arc</sup>Net: Transfer Learning Method for Low-Energy Series DC Arc-Fault Detection in Photovoltaic Systems

Sung, Yoondong; Yoon, Gihwan; Bae, Ji‐Hoon; Chae, Su Young

doi:10.1109/access.2022.3208115

Cited by 14 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 presents an overview of the detection accuracy achieved by the various approaches, including DAFD [33], TL-LED Arc Net [34], and DA-DCGAN [35], which exhibited accuracies of 95.76%, 95.8%, and 98.5%, respectively. In comparison, the proposed approach achieved an overall detection accuracy of 98.2%.…”

Section: S V Mmentioning

confidence: 99%

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

Dang,

Kwak,

Choi

2024

Machines

View full text Add to dashboard Cite

DC series arc faults pose a significant threat to the reliability of DC systems, particularly in DC generation units where aging components and high voltage levels contribute to their occurrence. Recognizing the severity of this issue, this study aimed to enhance DC arc fault detection by proposing an advanced recognition procedure. The methodology involves a sophisticated combination of current filtering using the Three-Sigma Rule in the time domain and the removal of switching noise in the frequency domain. To further enhance the diagnostic capabilities, the proposed method utilizes time and frequency signals generated from power supply-side signals as a reference input. The time–frequency features extracted from the filtered signals are then combined with artificial learning models. This fusion of advanced signal processing and machine learning techniques aims to capitalize on the strengths of both domains, providing a more comprehensive and effective means of detecting arc faults. The results of this detection process validate the effectiveness and consistency of the proposed DC arc failure identification schematic. This research contributes to the advancement of fault detection methodologies in DC systems, particularly by addressing the challenges associated with distinguishing arc-related distortions, ultimately enhancing the safety and dependability of DC electrical systems.

show abstract

Section: S V Mmentioning

confidence: 99%

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

Dang,

Kwak,

Choi

2024

Machines

View full text Add to dashboard Cite

show abstract

“…In [32], the lightweight convolutional neural network was utilized to diagnose the PV series arc. In [33], a transfer-learning-based detection network was utilized to identify the series arc through low energy. In [34], a series arc diagnostic algorithm based on ensemble machine learning was proposed.…”

Section: Introductionmentioning

confidence: 99%

Series Arc Fault Characteristics and Detection Method of a Photovoltaic System

Pang,

Ding

2023

Energies

View full text Add to dashboard Cite

The DC arc is the main cause of fire in photovoltaic (PV) systems. This is due to the fact that the DC arc has no zero-crossing point and is prone to stable combustion. Failure to detect it in a timely manner can seriously endanger the PV system. This study analyzes the influences of the series arc and the maximum power point tracking (MPPT) algorithm on the PV output characteristics based on the PV equivalent circuit module. The PV voltage and current variation characteristics are obtained when the series arc occurs. The findings indicate that the input voltage of the converter remains unchanged due to the MPPT algorithm before and after the series arc occurs. Furthermore, the PV faulty string output current will drastically decrease when the series arc fault occurs. On this basis, a series arc detection method based on the current change is proposed, suppressing the combustion of the series arc by increasing the target voltage of the MPPT algorithm. The experimental results show that the proposed method can effectively detect and extinguish the series arc in the PV system within 0.6 s. Compared to the other methods, the proposed method can be integrated into the PV system without additional hardware.

show abstract

Photovoltaic DC arc fault detection method based on deep residual shrinkage network

Zhang,

Xue,

Song

et al. 2024

J. Power Electron.

View full text Add to dashboard Cite

TL–LED^arcNet: Transfer Learning Method for Low-Energy Series DC Arc-Fault Detection in Photovoltaic Systems

Cited by 14 publications

References 32 publications

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

Series Arc Fault Characteristics and Detection Method of a Photovoltaic System

Photovoltaic DC arc fault detection method based on deep residual shrinkage network

Contact Info

Product

Resources

About

TL–LEDarcNet: Transfer Learning Method for Low-Energy Series DC Arc-Fault Detection in Photovoltaic Systems

Cited by 14 publications

References 32 publications

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

Series Arc Fault Characteristics and Detection Method of a Photovoltaic System

Photovoltaic DC arc fault detection method based on deep residual shrinkage network

Contact Info

Product

Resources

About

TL–LED^arcNet: Transfer Learning Method for Low-Energy Series DC Arc-Fault Detection in Photovoltaic Systems