ORIGINAL RESEARCH article
Front. Electron.
Sec. Power Electronics
Volume 6 - 2025 | doi: 10.3389/felec.2025.1656864
A high-precision fault diagnosis method for photovoltaic arrays considering the effect of missing data
Provisionally accepted- Beijing Fibrlink Communications Co., LTD., Beijing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
With the increasing penetration of photovoltaic (PV) systems into power grids, accurate diagnostics of PV array health has become critical for ensuring the stable operation of the power system. Aiming at the problems of missing data collected from PV arrays and reduced diagnostic accuracy when compound faults occur, a high-precision fault diagnosis model for PV arrays based on Tucker decomposition-Sparrow Search Algorithm (SSA)-Informer-MSCNet is proposed. First, a tensor Tucker decomposition-based method is proposed to complete the missing data. Then, informer network is employed to fully extract the global features. And a MSCNet model is proposed to extract multi-scale key features. Then we use the SSA 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 designed complementary algorithm has some accuracy. And 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.
Keywords: Power system, Tucker decomposition, missing data, Informer, Fault diagnosis
Received: 10 Jul 2025; Accepted: 17 Sep 2025.
Copyright: © 2025 Liu, Zhu and Du. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Di Liu, 13691589741@163.com
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.