An Intelligent Fault Detection Scheme for AC Microgrid: Based on Multilayer Perceptron

In the evolving landscape of renewable energy systems, ensuring the reliability and efficiency of AC microgrids is paramount. This paper presents an intelligent fault detection scheme for AC microgrids, leveraging Empirical Mode Decomposition (EMD) for signal decomposition and feature extraction, coupled with a Multilayer Perceptron (MLP) for fault detection and classification. EMD effectively decomposes complex electrical signals into intrinsic mode functions (IMFs), facilitating the extraction of significant fault-related features. These features are then fed into an MLP, a type of artificial neural network, which is trained to detect and classify faults with high accuracy. The proposed scheme demonstrates superior performance in identifying various fault types, ensuring robust protection and operational stability for AC microgrids.