EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advanced Multi-Scale CNN-BiLSTM for Robust Photovoltaic Fault Detection

Xiaojuan Zhang, Bo Jing, Xiaoxuan Jiao, Ruixu Yao

Sensors · 18.07.2025 · 25 (14) · 4474

DOI: 10.3390/s25144474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.07.2025. Verfasst von Xiaojuan Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Aeronautics Engineering, Air Force Engineering University, Xi'an 710051, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Lab of Aerospace Power System and Plasma Technology, Air Force Engineering University, Xi'an Science and Technology Plan Project, titled "Development of a Bus-based Multi-channel Inte-grated DC-DC Special Power Supply for Unmanned Aerial Vehicles", National Key Lab of Aerospace Power System and Plasma Technology, Air Force Engineering University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing deployment of photovoltaic (PV) systems necessitates robust fault detection mechanisms to ensure operational reliability and safety. Conventional approaches, however, struggle in complex industrial environments characterized by high noise, data incompleteness, and class imbalance. This study proposes an innovative Advanced CNN-BiLSTM architecture integrating multi-scale feature extraction with hierarchical attention to enhance PV fault detection. The proposed framework employs four parallel CNN branches with kernel sizes of 3, 7, 15, and 31 to capture temporal patterns across various time scales. These features are then integrated by an adaptive feature fusion network that utilizes multi-head attention. A two-layer bidirectional LSTM with temporal attention mechanism processes the fused features for final classification. Comprehensive evaluation on the GPVS-Faults dataset using a progressive difficulty validation framework demonstrates exceptional performance improvements. Under extreme industrial conditions, the proposed method achieves 83.25% accuracy, representing a substantial 119.48% relative improvement over baseline CNN-BiLSTM (37.93%). Ablation studies reveal that the multi-scale CNN contributes 28.0% of the total performance improvement, while adaptive feature fusion accounts for 22.0%. Furthermore, the proposed method demonstrates superior robustness under severe noise (σ = 0.20), high levels of missing data (15%), and significant outlier contamination (8%). These characteristics make the architecture highly suitable for real-world industrial deployment and establish a new paradigm for temporal feature fusion in renewable energy fault detection.

Schlagwörter

Stichwörter der Autor:innen

fault detectionhierarchical attentionmulti-scale CNNtemporal analysis

Autor:innen und Institutionen

  • College of Aeronautics Engineering, Air Force Engineering University, Xi'an 710051, China.
  • College of Mechanical Engineering, Xijing University, Xi'an 710123, China.
  • College of Artificial Intelligence, Xi'an Jiaotong University, Xi'an 710049, China.

Förderung

  • the National Key Lab of Aerospace Power System and Plasma Technology, Air Force Engineering University
  • Xi'an Science and Technology Plan Project, titled "Development of a Bus-based Multi-channel Inte-grated DC-DC Special Power Supply for Unmanned Aerial Vehicles"
  • National Key Lab of Aerospace Power System and Plasma Technology, Air Force Engineering University
  • Xi’an Science and Technology Plan Project

Zitieren

APA

Zhang, X., Jing, B., Jiao, X., & Yao, R. (2025). Advanced Multi-Scale CNN-BiLSTM for Robust Photovoltaic Fault Detection. Sensors, 25(14), 4474. https://doi.org/10.3390/s25144474

Vancouver

Zhang X, Jing B, Jiao X, Yao R. Advanced Multi-Scale CNN-BiLSTM for Robust Photovoltaic Fault Detection. Sensors. 2025;25(14):4474. doi:10.3390/s25144474

BibTeX
@article{Zhang2025,
  author = {Zhang, Xiaojuan and Jing, Bo and Jiao, Xiaoxuan and Yao, Ruixu},
  title = {Advanced Multi-Scale CNN-BiLSTM for Robust Photovoltaic Fault Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4474},
  doi = {10.3390/s25144474}
}
Kostenlos starten →