2026 Guzman Aerospace Power System Fault Detection

The transition toward More Electric Aircraft (MEA) has introduced highly complex electrical architectures that impose strict requirements on reliability, safety, and realtime operation. Yet most existing research on power quality disturbances (PQDs) and electrical fault diagnosis targets conventional utility-scale power grids and relies on low-frequency analysis, which limits accuracy and applicability in aircraft electrical systems that operate at higher frequencies. This paper addresses this gap by presenting a deep learning-based framework for automated multiclass detection and classification of electrical faults and PQDs in aircraft electrical systems with emphasis on classification metrics, robustness, and applicability under aerospace constraints. A high-fidelity aircraft power system model inspired by the Boeing 787 electrical architecture was developed to represent operation at a 400Hz fundamental frequency. The model produced high-resolution signals under a comprehensive set of fault and PQD conditions. Two datasets were produced, one consisting of one-dimensional time-domain signals and another of two-dimensional time-frequency representations. Several deep learning architectures were evaluated, including 1DCNNs, 2D-CNNs, LSTMs, and established networks like ResNet, demonstrating a compact ResNet architecture for effective classification.