Recently, fault detection has played a crucial role in ensuring the safety and reliability of inverter operation. Switch failures are primarily classified into Open-Circuit (OC) and short-circuit faults. While OC failures have limited negative impacts, prolonged system operation under such conditions may lead to further malfunctions. This paper demonstrates the effectiveness of employing Artificial Intelligence (AI) approaches for detecting single OC faults in a Packed E-Cell (PEC) inverter. Two promising strategies are considered: Random Forest Decision Tree (RFDT) and Feed-Forward Neural Network (FFNN). A comprehensive literature review of various fault detection approaches is first conducted. The PEC inverter’s modulation scheme and the significance of OC fault detection are highlighted. Next, the proposed methodology is introduced, followed by an evaluation based on five performance metrics, including an in-depth comparative analysis. This paper focuses on improving the robustness of fault detection strategies in PEC inverters using MATLAB/Simulink software. Simulation results show that the RFDT classifier achieved the highest accuracy of 93%, the lowest log loss value of 0.56, the highest number of correctly predicted estimations among the total samples, and nearly perfect ROC and PR curves, demonstrating exceptionally high discriminative ability across all fault categories.

Recently, fault detection has proven its crucial role in guaranteeing the safety and dependability of inverter functioning. This paper demonstrates the effectiveness of employing Artificial Intelligence (AI) approaches for fault detection of single Open Circuit (OC) switch fault in a Packed E-Cell (PEC) inverter. Two optimum strategies have been considered Random Forest Decision Tree (RFDT) and Feedforward Neural Network (FFNN). Initially, Discrete Wavelet Analysis (DWA) is employed for the investigation of the output voltage, using the first level of detailed coefficients. After that, three statistical features are extracted from this analysis to serve as input to the classifier during learning. The output of the classifier, which is referred to the fault class, is then trained according to each strategy process. Finally, a comparison with deep analysis based on selected criteria is illustrated and the results obtained using MATLAB/Simulink confirm the comprehensive review of the evaluated strategies.