Abstract
This paper proposes an improved method for fault diagnosis on the DC side of PV plant. The proposed technique relies on three-stage classification algorithms to detect and distinguish between eight of the most common faults occurring in the PV generator. The first part of the detection algorithm uses the power loss analysis approach to identify the presence of potential fault from the comparison of the measured and expected generated power. The second part relies on a comparison between the extracted and reference PV characteristic to identify the fault type. The last part is based on Support Vector Machine (SVM) algorithm that interferes to classify faults with the same signature. The simulation results have proven that the proposed method is capable of identifying and distinguishing between eight of the most common DC side faults with a 100% accuracy.
