Recently, fault detection has played an essential role in ensuring the safety and reliability of inverter operation. This paper illustrates the efficiency of employing the random forest decision tree approach for fault detection of single open circuit switch fault in a Packed E-Cell inverter. First, Discrete Wavelet Analysis is utilized to analyze the output voltage, using the first level of detailed coefficients. Then, three statistical features are extracted from this analysis to serve as input to the classifier during training. The output of the classifier, which indicates the fault status, is then trained accordingly. Finally, a fault detection strategy is implemented, and the results obtained using MATLAB/Simulink affirm the effectiveness of the proposed algorithm highlighting its high accuracy and robustness.

Multilevel Inverters (MLI) have become important for electrical energy supplement to grids due to their modularity, lower Total Harmonic Distortion (THD), and decreased filter needs. Recently, a new compact MLI has been introduced named Packed E Cell (PEC) inverter, where an auxiliary dc-link cell is made along with the shunted capacitors. This paper proposes a new switching controller using redundant states in signal builder blocks to balance voltage capacitors. Simulation results have shown the optimum operation of PEC topology and validated the proposed technique.

Multi-Level Inverters (MLI) have become of great importance for electrical energy supplement to grids due to its modularity, lower Total Harmonic Distortion (THD) and decreased filter needs. However, although multilevel inverters achieve high voltage levels, increased number of power switches are required which make them more prone to breakdowns and faults. Among active devices failures, Open-Circuit (OC) faults are extensively explored in research studies. Hence, this paper presents a deep overview concerning methods based on Artificial Intelligence (AI) algorithms involved in diagnosis and localization of OC failure in different multilevel inverter architectures. Initially, two major classifications of fault diagnosis methods for OC switch failure are listed and clarified briefly. Then, AI algorithms are discussed thoroughly. Further, certain criteria with several standards are formulated to differentiate between strategies investigated in publications. Then, various implemented techniques in literature are widely overviewed and compared in an original table.