Hybrid Feature-Based and Optimized Classification Algorithm for Arc Fault Detection in Hybrid AC/DC Microgrid

The increasing penetration of distributed renewable energy sources (DRES) in hybrid AC/DC micro grids (HAC/DCµG) introduces signi cant safety concerns. Among these, arc faults (AFs) on the DC side pose a particular risk due to the absence of natural current zero-crossing, making detection and protection more challenging compared to AC systems. AFs are unavoidable during normal operating conditions due to dielectric breakdown. They can cause re hazards, system malfunctions, and even fatalities. To address this issue, this study proposes an AF detection framework that captures AF V-I characteristics using both linear (LAF ) and non-linear (NAF ) AF modeling. A feature extraction approach is applied to arc voltage and current signals, where statistical time-domain features are com bined with frequency-domain features obtained using the Fast Fourier Transform (FFT). These features are then used to train a Deep Fully Connected Neural Network (DFCNN) with three hidden layers, enhancing the detection capability. To further enhance detection accuracy and develop a highly precise AF detection model, the DFCNN is optimized using the Pelican Optimization Algorithm, which ne tunes its parameters for superior performance. The mathematical models of LAF and NAF models are developed and implemented in MATLAB Simulink. Additionally, an AF generator setup is designed and operated on the Electron A0240 HAC/DC platform to emulate real-time AF tests. The ndings indicate that the proposed approach improves classi cation performance compared to other classi ers. The framework integrates the modeling of both LAF and NAF models, time-frequency domain features, and optimized DFCNN classi cation to evaluate AF detection in HAC/DCµG, achieving a detection accuracy of 98.97% with an average detection time of 45 ms.