DetectivePV: A Detection Package for Electrical Faults in Photovoltaic Arrays based on Machine Learning

Conventional protection devices in PV arrays may not be able to detect line-line (LL) and line-ground (LG) faults due to these faults are not detectable under high fault impedance and low mismatch level. In recent years, many efforts have been devoted to overcome these challenges using intelligent methods. However, these methods could not classify the type of faults and diagnose their severity. This paper proposes DetectivePV which is a novel and intelligent fault monitoring package to detect and classify LL and LG faults at the DC side of PV systems. In this package, firstly, the main features of PV array current-voltage (I-V) curves under different fault events and normal conditions are extracted. Then the faults are classified using a machine learning (ML)-based Hierarchical Classification (HC) platform. DetectivePV package aims to reduce the amount of dataset which is required for the ML algorithms training process and still obtain a high accuracy in detecting and classifying the fault events especially at low mismatch levels and high fault impedance. The experimental output results of DetectivePV verify that the package precisely detects and classifies LL and LG faults in PV systems under different conditions with the accuracy of 96.66% and 91.66%, respectively.