研究人员开发了JEFFNet，这是一种利用热红外成像对太阳能光伏（PV）板故障进行分类的新型架构。该多分支模型结合了来自联合嵌入预测架构（JEPA）的自监督学习和来自EfficientNetV2-S的监督特征提取。JEFFNet在PVF-10和InfraredSolarModules（ISM）两个数据集上表现出色，在多类和二元故障分类中均取得了高F1分数和准确率。值得注意的是，与GEPFNet等现有方法相比，JEFFNet的参数效率也更高。 AI
影响 这项研究可能带来更高效、更准确的太阳能基础设施维护方法。
排序理由 该集群描述了一篇详细介绍新型AI架构及其在特定数据集上性能的新研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.09205v1 Announce Type: cross Abstract: 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 solut…
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 c…