Photovoltaic panel artifact

What is PVL-AD dataset for photovoltaic panel defect detection?

To meet the data requirements, Su et al. 18 proposed PVEL-AD dataset for photovoltaic panel defect detection and conducted several subsequent studies 19, 20, 21 based on this dataset. In recent years, the PVEL-AD dataset has become a benchmark for photovoltaic (PV) cell defect detection research using electroluminescence (EL) images.

What are the different types of defects in PV panels?

As illustrated in Fig. 1, the common types of defects in PV panels include crack, finger interruption, black core, thick line, star crack, corner, horizontal dislocation, vertical dislocation, and short circuit often accompanied by complex background interference. However, defect detection in EL images requires highly specialized knowledge.

How machine vision is used in photovoltaic panel defect detection?

Machine vision-based approaches have become an important direction in the field of defect detection. Many researchers have proposed different algorithms 11, 15, 16 for photovoltaic panel defect detection by creating their own datasets.

How to identify a defect on a panel from a PV array?

The test procedure of identifying a defect on a panel from a PV array by eliminating the background information is carried out in 8 steps as depicted below: Step 1: The thermal images of the PV modules operating normally and with various faults are captured. These captured thermal images may be affected by the refection from external objects.

Can El images be used for photovoltaic panel defect detection?

Buerhop et al. 17 constructed a publicly available dataset using EL images for optical inspection of photovoltaic panels. Based on this dataset, researchers have developed numerous algorithms 9, 10, 12 for photovoltaic panel defect detection.

Is Yolo-ACF a good choice for defect detection on photovoltaic panels?

Through qualitative and quantitative comparisons with various alternative methods, we demonstrate that our YOLO-ACF strikes a good balance between detection performance, model complexity, and detection speed for defect detection on photovoltaic panels. Moreover, it demonstrates remarkable versatility across a spectrum of defect types.