An Intelligent-Based Fault-Tolerant System for Solar-Fed Cascaded Multilevel Inverters

This paper presents an intelligent-based fault-tolerant system for a solar photovoltaic (PV) inverter. Artificial neural network based controller is used to monitor, detect, and diagnose the faults in solar PV panels, battery, semiconductor switches, and inverters. The cascaded multilevel inverter is connected across the combination of solar PV panel and battery for dc-ac conversion. The major advantage of the proposed topology is that it can deliver power from source to the load even under fault and partial shaded conditions. The paper also reviews on various faults in the solar PV energy conversion process and provides suitable solutions for each circumstance. Simulations are undertaken in MATLAB 2016a/Simulink and experimental investigation is carried out for a 3 kWp solar PV system. The results have proven that the system is capable to deliver power in spite of faulty environments. The comparison and discussion of the results were made to show the effectiveness of the proposed system.