Unsupervised defect detection for solar photovoltaic cells based on convolutional autoencoder

Solar photovoltaic (PV) cells are inevitably subject to defects during the production process, affecting their power generation efficiency and life. Electroluminescence (EL) imaging is the mainstream non-destructive method for PV cell defect detection. Aiming at PV cell EL images, an unsupervised de...

Full description

Saved in:
Bibliographic Details
Published in:Nondestructive testing and evaluation Vol. 40; no. 12; pp. 6143 - 6159
Main Authors: Zhang, Yufei, Zhang, Xu, Tu, Dawei
Format: Journal Article
Language:English
Published: Abingdon Taylor & Francis 02.12.2025
Taylor & Francis Ltd
Subjects:
convolutional autoencoder
Defect detection
Defects
Nondestructive testing
Perception
Performance measurement
Photovoltaic cells
PV cell
Solar cells
unsupervised learning
ISSN:1058-9759, 1477-2671
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Solar photovoltaic (PV) cells are inevitably subject to defects during the production process, affecting their power generation efficiency and life. Electroluminescence (EL) imaging is the mainstream non-destructive method for PV cell defect detection. Aiming at PV cell EL images, an unsupervised defect detection method was proposed. Specifically, an unsupervised convolutional autoencoder (CAE), the scale structure perception convolutional autoencoder (SSP_CAE), was constructed, whose Squeeze-and-Excitation Attention (SE Attention) and skip connections avoid the blurring of image structure information and the loss of pixel-level details in the encoding and decoding process. Furthermore, to balance the global and local information of the image, a scale perception loss function called SP_SSIM was proposed for model training. The defect segmentation was achieved by using Otsu thresholding method to binarize the obtained Mean Absolute Error (MSE) residual heat image in the testing stage of the model. Finally, the experiments were performed on the test dataset and the experimental results showed that the proposed SSP_CAE can effectively detect PV cell defects. The experimentally obtained defect detection performance metrics Precision, Recall, IoU, F1-score and AUROC values were 0.739, 0.886, 0.723, 0.764 and 0.841, respectively. Compared with other classical methods, the proposed SSP_CAE had a better comprehensive performance for defect detection.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1058-9759
1477-2671
DOI:10.1080/10589759.2025.2456673