A high-precision fault diagnosis method for photovoltaic arrays considering the effect of missing data

With the increasing penetration of photovoltaic (PV) systems into power grids, the accurate diagnosis of PV array health has become critical for ensuring the stable operation of power systems. To address the problem of missing data collected from PV arrays and reduced diagnostic accuracy when compound faults occur, we propose a high-precision fault diagnosis model for PV arrays based on Tucker decomposition-sparrow search algorithm (SSA)-Informer-MSCNet. First, a tensor Tucker decomposition-based method is proposed to complete the missing data. Then, an informer network is employed to fully extract the global features. Next, an MSCNet model is proposed to extract multi-scale key features. The SSA is then used to optimize the model’s global parameters. We use the fault dataset to realize the missing data completion and fault diagnosis tests of PV arrays. The results show that the complementary algorithm thus designed has some accuracy. The proposed fault diagnostic model is able to achieve 98.73% and 97.46% accuracy in case of single and compound faults in PV arrays, respectively, and maintains 96.12% accuracy at 30 dB noise.