New Feature Extraction Method for Photovoltaic Array Output Time Series and Its Application in Fault Diagnosis
Honglu Zhu, Yucheng Shi, Haizheng Wang, Lingxing Lu
Abstract
Photovoltaic array produces massive running data, and such data are time series of strong coupling features with each other. In addition, photovoltaic output data has a strong fluctuating and nonlinear feature; it brings extra difficulty to photovoltaic array fault feature extraction and its fault diagnosis. To solve these problems, this article proposes a fault diagnosis method using the time series features for photovoltaic array. The features of the photovoltaic array output are described in this article. From the perspective of distance analysis and similarity analysis, this article proposes a feature extraction method for photovoltaic array output time series, and features of output time series under different fault conditions are analyzed. Taking similarity index and distance index as input, the fuzzy system is built for identifying faults for photovoltaic array. The operational data analysis shows that the time series feature indexes proposed can successfully characterize different fault types, and this method can effectively diagnose typical faults of photovoltaic array.