String-Level Ground Fault Localization for TN-Earthed Three-Phase Photovoltaic Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917275335917568 |
|---|---|
| author | Li, Yuanliang Gong, Xun Iravani, Reza Cao, Bo Liu, Heng Chen, Ziming |
| author_facet | Li, Yuanliang Gong, Xun Iravani, Reza Cao, Bo Liu, Heng Chen, Ziming |
| contents | The DC-side ground fault (GF) poses significant risks to three-phase TN-earthed photovoltaic (PV) systems, as the resulting high fault current can directly damage both PV inverters and PV modules. Once a fault occurs, locating the faulty string through manual string-by-string inspection is highly time-consuming and inefficient. This work presents a comprehensive analysis of GF characteristics through fault-current analysis and a simulation-based case study covering multiple fault locations. Building on these insights, we propose an edge-AI-based GF localization approach tailored for three-phase TN-earthed PV systems. A PLECS-based simulation model that incorporates PV hysteresis effects is developed to generate diverse GF scenarios, from which correlation-based features are extracted throughout the inverter's four-stage shutdown sequence. Using the simulated dataset, a lightweight Variational Information Bottleneck (VIB)-based localization model is designed and trained, achieving over 93% localization accuracy at typical sampling rates with low computational cost, demonstrating strong potential for deployment on resource-constrained PV inverters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12289 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | String-Level Ground Fault Localization for TN-Earthed Three-Phase Photovoltaic Systems Li, Yuanliang Gong, Xun Iravani, Reza Cao, Bo Liu, Heng Chen, Ziming Systems and Control Machine Learning Signal Processing The DC-side ground fault (GF) poses significant risks to three-phase TN-earthed photovoltaic (PV) systems, as the resulting high fault current can directly damage both PV inverters and PV modules. Once a fault occurs, locating the faulty string through manual string-by-string inspection is highly time-consuming and inefficient. This work presents a comprehensive analysis of GF characteristics through fault-current analysis and a simulation-based case study covering multiple fault locations. Building on these insights, we propose an edge-AI-based GF localization approach tailored for three-phase TN-earthed PV systems. A PLECS-based simulation model that incorporates PV hysteresis effects is developed to generate diverse GF scenarios, from which correlation-based features are extracted throughout the inverter's four-stage shutdown sequence. Using the simulated dataset, a lightweight Variational Information Bottleneck (VIB)-based localization model is designed and trained, achieving over 93% localization accuracy at typical sampling rates with low computational cost, demonstrating strong potential for deployment on resource-constrained PV inverters. |
| title | String-Level Ground Fault Localization for TN-Earthed Three-Phase Photovoltaic Systems |
| topic | Systems and Control Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2602.12289 |