Abstract This paper proposes a novel data-driven approach for hot-spot fault detection in photovoltaic (PV) modules, utilizing a curved Riemannian manifold (RM) to characterize the sample space. The proposed method detects hot spots in PV systems by mining geometric features in high-dimensional data. The RM-based method combines the geometric properties of Riemannian manifolds for fault detection. In addition, it also provides information about the severity of the hot spots. The proposed method has three main advantages:
1) it is capable of actively learning fault characteristics and can be applied to diagnose various degrees of hot spots;
2) unlike other data-driven methods, the proposed method considers non-Euclidean spatial data features, which further improves the accuracy of the method and reduces the false alarm rate (FAR);
3) it does not rely on mathematical models or expert knowledge, making it able to meet the real-time monitoring needs of actual PV systems.
The effectiveness and superiority of the proposed approach are verified through 12 sets of hot spots tests conducted on a PV experimental platform.