Research area: Machine Learning Authors: Ian C. Guzmán, Radu Babiceanu, Berker Peköz Published: 2026-09-09 arXiv: 2609.10479
Abstract
More Electric Aircraft require fast and reliable monitoring of high-frequency electrical networks, yet most power quality disturbance and fault diagnosis methods are developed for conventional 50 or 60 Hz grids. This work presents a hardware-aware deep learning framework for multiclass detection of electrical faults and power quality disturbances in a 400 Hz aerospace power system. A high-fidelity simulation model inspired by the Boeing 787 electrical architecture generates voltage and current waveforms for 21 normal, disturbance, switching, open-circuit, and short-circuit conditions. Two datasets, each containing 73,500 samples, are formed from one-dimensional time-series signals and short-time Fourier transform time-frequency representations. Signal-processing augmentation, domain randomization, and class-specific generative adversarial networks increase waveform diversity, and the time-series dataset is released through IEEE DataPort. We compare 1D and 2D convolutional neural networks, long short-term memory networks, CNN-LSTM hybrids, ResNet, MobileNet, and VGG models under common training conditions. A compact ResNet provides the best accuracy-complexity tradeoff, achieving 96.94 percent software test accuracy with 175,685 parameters. After 8-bit quantization and deployment on a Xilinx Zynq UltraScale Plus MPSoC ZCU102, the model achieves 95.87 percent accuracy and a measured mean neural-network accelerator latency of 6.90 ms per input record. The results establish simulation-based, accelerator-level feasibility for embedded edge AI in aircraft electrical health monitoring and motivate future end-to-end data acquisition and experimental validation.
Key Points
- Targets 400 Hz aerospace power systems rather than conventional 50/60 Hz grids
- Simulation model inspired by the Boeing 787 electrical architecture covers 21 fault/disturbance classes
- Two 73,500-sample datasets: 1D time-series and STFT time-frequency representations; time-series data released on IEEE DataPort
- Augmentation via signal processing, domain randomization, and class-specific GANs
- Compact ResNet wins the benchmark: 96.94% accuracy with 175,685 parameters
- 8-bit quantized deployment on Xilinx ZCU102 MPSoC: 95.87% accuracy, 6.90 ms mean accelerator latency