A Fault Diagnosis Method for PV Arrays Based on New Feature Extraction and Improved the Fuzzy C-Mean Clustering

• Published in: IEEE journal of photovoltaics Vol. 12; no. 3; pp. 833 - 843
• Main Authors: Xu, Liuchao, Pan, Zhiheng, Liang, Chuandong, Lu, Min
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Arrays; Circuit faults; Clustering; Clustering algorithms; Degradation; Fault detection; Fault diagnosis; Faults; Feature extraction; fuzzy C-mean clustering (FCM) algorithm; ICMMD; Integrated circuit modeling; Parameters; photovoltaic (PV) array; Photovoltaic cells; Resistance
• ISSN: 2156-3381; 2156-3403
• DOI: 10.1109/JPHOTOV.2022.3151330

Photovoltaic (PV) array fault diagnosis is vital for the safe and stable operation of PV systems. Up to now, there are many methods to diagnose and classify PV array faults successfully. However, the difficulty of fault diagnosis is increased because the PV arrays have nonlinear output characteristics and complex working environments. In practice, the difference in characteristic parameters of different faults is not apparent, and it is not easy to effectively obtain labels of many samples. In order to address the above problems, this article proposes a new fault detection method for PV arrays based on the output current-voltage ( I - V ) characteristic, an improved fuzzy C-mean clustering (FCM) algorithm to identify four common PV array faults. The measured I - V characteristic curves are used to extract the initial feature parameters and then calculate the initial parameters to obtain characteristic parameters. In addition, it used characteristic parameters as feature variables of the FCM fault diagnosis model. Finally, classification results are verified by inner cluster maximum mean discrepancy and reclassification pseudoparameter based on the relationship between characteristic parameters. This method defines new characteristic parameters and achieves the purpose of fault detection by reclassification; in addition, we verify the high accuracy and simplicity of the method through simulation and experiment.