Fault Diagnosis and Localization of Solar Photovoltaic Fed Cascaded H-Bridge Multi-Level Inverter

Abstract

This research introduces a deep learning approach for detecting and localizing switch faults in Photovoltaic (PV) systems, specifically targeting PV fed cascaded H-bridge 5-level inverters. The study’s primary focus is on identifying both single short circuit faults and up to two open switch faults, aiming to enhance the reliability of this inverter. The research utilizes a Residual Network (ResNet) architecture with residual connections to effectively identify and localize faults. Extensive testing across 48 unique fault classes and one non fault case demonstrated the model’s robustness, achieving an accuracy of 92% at -20 dB noise, approximately 94% at -10 dB and 0 dB, and around 95% at 10 dB and 20 dB. The model was trained using NVIDIA A100 GPU. This research highlights the development of a real-time fault detection system capable of operating under multiple modulation indices, ranging from 0.55 to 1, in the presence of both single and double switch faults. By incorporating noise signals, the study addresses practical challenges in solar inverter operations and advances the methodology for detection of fault in PV systems. The results underscore the potential of proposed methodology to markedly improve upon the reliability and performance of renewable energy technologies, marking a progressive step in fault detection for solar energy systems.