A researcher at Husqvarna Group, a Swedish outdoor power products manufacturer, has developed a novel, lightweight, and interpretable framework for a real-time PV fault-detection method.
The technique employs infrared (IR) thermography and, rather than relying on common image feature descriptors based on high-dimensional texture, utilizes analysis in the uniform Lab* color space. Lab* is widely used in printing, photography, design, manufacturing, and color science because it is device-independent and perceptually uniform. By separating luminance (L) from chromaticity (a and b), it enhances the detection of surface-level degradations.
“This work presents a novel, application‑focused approach to multi‑hotspot detection that departs from prevailing PV thermography trends,” the researcher Waqas Ahmed told pv magazine. “Rather than relying on convolutional neural networks or high‑dimensional texture descriptors, I propose a patch‑wise feature extraction pipeline based on the perceptually uniform Lab* color space, producing a compact vector of 80 statistical descriptors per image.”
“The new design prioritizes interpretability, computational efficiency, and robustness to illumination and environmental variability, making it suitable for drone, handheld, and embedded edge deployments,” Ahmed further explained. “It was surprising to see how the new technique achieved strong hotspot discrimination, even comparable to much heavier models, while remaining robust across varying illumination and survey conditions.”
The novel method begins by capturing IR thermographs of PV modules in operation at 640×512 pixels and converting them from their original channels to the L*, a*, b* color space. Each image is then sliced into 16 patches of 64×64 pixels to enable local fault detection.
The system then extracts two statistics from the L* channel (mean and standard deviation) and three from the b* channel (mean, standard deviation, and entropy). Overall, each image yields 80 features, with five features extracted from each of the 16 segments. Accordingly, shallow classifiers can be trained to extract features.
To demonstrate the new method, Ahmed has collected IR data from a 44.24 kW rooftop PV system located in Lahore, Pakistan. The system comprised 376 PV modules, each rated at 240 W, organized into eight strings, with 22 modules connected in series per string, for a total of 5.28 kW per string.
Thermal imaging was conducted while ambient temperatures ranged from 32 C to 40 C, wind velocity was 6.9 m/s, and solar irradiance was at or above 700 W/m2. The researcher then categorized 309 IR thermographs as healthy, hot-spot, or faulty panels.
The dataset was then randomly split into 80% for training (246 images) and 20% for testing (63 images), with equal representation of hotspot subtypes. Then, it was fed into a suite of shallow classifiers, namely SVM, KNN, Decision Tree, Naive Bayes, and Ensemble. SVM was found to achieve a test accuracy of 95.2%, KNN 93.7%, and the ensemble 90.5%. Naive Bayes achieved 84.1% test accuracy, and the decision tree achieved 81.0%.
“The method demonstrates sub‑6‑second training latency on edge platforms and reports measurable system‑level benefits preserving up to 17,620 kWh annually and mitigating 8.9 t CO₂, thereby linking algorithmic novelty to operational and environmental impact,” Ahmed concluded. “My next work, together with my colleague Manahil Zulfiqar, will focus on label noise and misannotation in PV datasets for AI applications. We will investigate methods to detect and correct mislabeled examples, separate overlapping hotspot subclasses, and combine cross‑modal consistency checks, uncertainty estimation, and active relabeling to improve field reliability.”
The new method was presented in “Thermal and chromatic analysis for scalable photovoltaic hotspot detection,” published in Solar Energy. Ahmed is affiliated with Sweden’s Husqvarna Group, Jönköping University, and the United Kingdom’s Imperial College London.
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com.
By submitting this form you agree to pv magazine using your data for the purposes of publishing your comment.
Your personal data will only be disclosed or otherwise transmitted to third parties for the purposes of spam filtering or if this is necessary for technical maintenance of the website. Any other transfer to third parties will not take place unless this is justified on the basis of applicable data protection regulations or if pv magazine is legally obliged to do so.
You may revoke this consent at any time with effect for the future, in which case your personal data will be deleted immediately. Otherwise, your data will be deleted if pv magazine has processed your request or the purpose of data storage is fulfilled.
Further information on data privacy can be found in our Data Protection Policy.