发表机构
University of Oulu; Central Queensland University（奥卢大学; 中央昆士兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究太阳能光伏板热红外图像故障分类，提出JEFFNet多分支架构，结合自监督语义与监督卷积特征，在PVF-10和ISM数据集上实验，相比GEPFNet参数大幅减少，有效提升分类性能。
AI 中文摘要
太阳能光伏（PV）系统的迅速扩张增加了对可靠且可扩展的故障分类的需求，因为大规模人工检查不切实际。热红外（IR）成像为识别光伏故障提供了非接触式解决方案；然而，由于类别不平衡、纹理信息有限和细微的热差异，准确分类仍具有挑战性。在这项工作中，我们研究了联合嵌入预测架构（JEPA）在各种场景下对热红外光伏故障分类的适用性，并提出了JEFFNet（基于JEPA的高效网络），这是一种多分支架构，它将基于JEPA的自监督表示学习与基于EfficientNetV2-S的监督卷积特征提取相结合。JEFFNet将来自JEPA预训练视觉Transformer的语义表示与EfficientNetV2-S的卷积特征相融合，实现互补特征学习。JEFFNet在两个公共热红外数据集PVF-10和红外太阳能模块（ISM）上进行多类别和派生二分类（健康/故障）评估。在PVF-10上，JEFFNet在10类任务中F1分数达到93.21，准确率为94.33，在派生的2类任务中F1分数为97.53，准确率为96.41。在ISM上，JEFFNet在12类任务中F1分数为72.60，准确率为83.88，在派生的2类任务中F1分数为94.69，准确率为94.78。JEFFNet仅使用1.亿零860万个参数，而GEPFNet为2.亿零5910万个，减少了47.2%。这些结果表明，结合自监督语义和监督卷积特征为热红外光伏故障分类提供了一种有效且参数高效的解决方案。源代码可在该https网址公开获取。
英文摘要
The rapid expansion of solar photovoltaic (PV) systems has increased the need for reliable and scalable fault classification, as manual inspection is impractical at scale. Thermal infrared (IR) imaging provides a non-contact solution for identifying PV faults; however, accurate classification remains challenging due to class imbalance, limited texture information, and subtle thermal differences. In this work, we investigate the applicability of Joint-Embedding Predictive Architecture (JEPA) for thermal IR PV fault classification across various scenarios and propose JEFFNet (JEPA-EFFicientNet), a multibranch architecture that combines JEPA-based self-supervised representation learning with EfficientNetV2-S-based supervised convolutional feature extraction. JEFFNet fuses semantic representations from a JEPA-pretrained Vision Transformer with convolutional features from EfficientNetV2-S, enabling complementary feature learning. JEFFNet is evaluated on two public thermal IR datasets, PVF-10 and InfraredSolarModules (ISM), for both multiclass and derived binary (healthy/faulty) classification. On PVF-10, JEFFNet achieves an F1-score of $93.21$ and an accuracy of $94.33$ in the 10-class task, and an F1-score of $97.53$ and an accuracy of $96.41$ in the derived 2-class task. On ISM, JEFFNet achieves an F1-score of $72.60$ and an accuracy of $83.88$ in the 12-class task, and an F1-score of $94.69$ and an accuracy of $94.78$ in the derived 2-class task. JEFFNet also uses only 108.6M parameters versus 205.91M for GEPFNet, a 47.2\% reduction. These results demonstrate that combining self-supervised semantic and supervised convolutional features provides an effective, parameter-efficient solution for thermal IR PV fault classification. The source code is publicly available at https://github.com/Azimi2kht/JEFFNet
