Archive | 2021
Transfer Learning-Based Novel Fault Classification Technique for Grid-Connected PV Inverter
Abstract
The reliability of grid-connected photovoltaic (PV) inverters is of extreme importance and plays a crucial role in maintaining the stability of the grid. In order to prepare the system for different kinds of uncertainties and failures, the identification of the system faults is essential. This paper presents a novel transfer learning-based fault detection and classification technique for grid connected single-phase PV inverters. To achieve this, the voltage and current outputs of the inverter are analyzed by simulating the inverter system for different failure conditions. Further, transfer learning-based classification scheme is utilized for the purpose of fault classification. This novel technique is implemented in MATLAB. Simulation results clearly spell out the efficacy of the proposed technique in terms of accuracy, reliability and robustness.