English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Increasing deployment of photovoltaic (PV) plants requires methods forautomatic detection of faulty PV modules in modalities, such as infrared (IR)images. Recently, deep learning has become popular for this. However, relatedworks typically sample train and test data from the same distribution ignoringthe presence of domain shift between data of different PV plants. Instead, weframe fault detection as more realistic unsupervised domain adaptation problemwhere we train on labelled data of one source PV plant and make predictions onanother target plant. We train a ResNet-34 convolutional neural network with asupervised contrastive loss, on top of which we employ a k-nearest neighborclassifier to detect anomalies. Our method achieves a satisfactory area underthe receiver operating characteristic (AUROC) of 73.3 % to 96.6 % on ninecombinations of four source and target datasets with 2.92 million IR images ofwhich 8.5 % are anomalous. It even outperforms a binary cross-entropyclassifier in some cases. With a fixed decision threshold this results in 79.4% and 77.1 % correctly classified normal and anomalous images, respectively.Most misclassified anomalies are of low severity, such as hot diodes and smallhot spots. Our method is insensitive to hyperparameter settings, convergesquickly and reliably detects unknown types of anomalies making it well suitedfor practice. Possible uses are in automatic PV plant inspection systems or tostreamline manual labelling of IR datasets by filtering out normal images.Furthermore, our work serves the community with a more realistic view on PVmodule fault detection using unsupervised domain adaptation to develop moreperformant methods with favorable generalization capabilities.

Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning