arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.08003cs.LGcs.AI
收藏

用于光伏组件故障检测的DTW k-means聚类

DTW k-means clustering for fault detection in photovoltaic modules

LAAS-CNRS;Université fédérale de Toulouse(图卢兹联邦大学);CNRS(法国国家科学研究中心);INSA(国立应用科学学院);UPS(图卢兹第三大学);Feedgy Solar;ANITI

Edgar Hernando Sepúlveda Oviedo, Louise Travé-Massuyès, Audine Subias, Marko Pavlov, Corinne Alonso

AI总结:

针对现有光伏故障检测方法依赖标注、难以适配大型电站等问题,提出结合DTW度量与K-means的无监督聚类方法,可区分正常与故障光伏面板,经目视检查标签验证有效。

摘要:

全球光伏(PV)能源使用量的增长表明,光伏电站的使用寿命和维护直接取决于快速检测光伏电站严重故障的能力。为解决这一检测问题,文献中已提出基于数据的方法。然而,这些以往的解决方案仅考虑一种或少数几种故障的特定行为。其中大多数方法可归为监督式方法,需要大量标注工作(每种技术中都要明确识别故障类型)。此外,大多数方法仅在光伏电池或单个光伏组件上验证,考虑到大型光伏电站的复杂性,这类方法几乎无法应用于其中。另一种思路是,一些知名的无监督数据驱动方法尝试检测异常,但无法精确识别故障类型。这些方法中性能最优的确实能有效将正常面板分组,并将其与故障面板区分开。基于此,本文提出一种名为DTW K-means的无监督方法。该方法结合了动态时间规整(DTW)度量和K-means聚类算法的优势,作为一种数据驱动方法。将这种混合方法在光伏串上的检测结果,与通过面板目视检查确定的诊断标签进行了对比。

英文摘要:

The increase in the use of photovoltaic (PV) energy in the world has shown that the useful life and maintenance of a PV plant directly depend on theability to quickly detect severe faults on a PV plant. To solve this problem of detection, data based approaches have been proposed in the literature.However, these previous solutions consider only specific behavior of one or few faults. Most of these approaches can be qualified as supervised, requiring an enormous labelling effort (fault types clearly identified in each technology). In addition, most of them are validated in PV cells or one PV module. That is hardly applicable in large-scale PV plants considering their complexity. Alternatively, some unsupervised well-known approaches based on data try to detect anomalies but are not able to identify precisely the type of fault. The most performant of these methods do manage to efficiently group healthy panels and separate them from faulty panels. In that way, this article presents an unsupervised approach called DTW K-means. This approach takes advantages of both the dynamic time warping (DWT) metric and the Kmeans clustering algorithm as a data-driven approach. The results of this mixed method in a PV string are compared to diagnostic labels established by visual inspection of the panels.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑