基于深度学习的航空航天电力系统电气故障与电能质量扰动检测
Deep Learning-Based Detection of Electrical Faults and Power Quality Disturbances in Aerospace Power Systems
- Embry-Riddle Aeronautical University（安柏瑞德航空大学）
- Western Michigan University（西密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多电飞机400赫兹电网，提出硬件感知深度学习框架，利用仿真数据训练紧凑ResNet，经量化部署后实现高精度故障检测，验证了嵌入式边缘AI的可行性。
AI中文摘要：
多电飞机需要对高频电网进行快速可靠的监测，然而大多数电能质量扰动和故障诊断方法是为传统的50或60赫兹电网开发的。本工作提出了一种面向硬件的深度学习框架，用于在400赫兹航空航天电力系统中对电气故障和电能质量扰动进行多类检测。一个受波音787电气架构启发的保真度仿真模型生成了21种正常、扰动、开关、开路和短路工况下的电压和电流波形。两个数据集，每个包含73,500个样本，分别由一维时间序列信号和短时傅里叶变换时频表示构成。信号处理增强、域随机化和类特定生成对抗网络增加了波形多样性，时间序列数据集已通过IEEE DataPort发布。我们在相同的训练条件下比较了一维和二维卷积神经网络、长短期记忆网络、CNN-LSTM混合模型、ResNet、MobileNet和VGG模型。一个紧凑的ResNet提供了最佳的精度-复杂度权衡，在175,685个参数下实现了96.94%的软件测试准确率。经过8位量化并在Xilinx Zynq UltraScale+ MPSoC ZCU102上部署后，该模型实现了95.87%的准确率，实测平均神经网络加速器延迟为每个输入记录6.90毫秒。研究结果确立了基于仿真的加速器级可行性，用于飞机电气健康监测中的嵌入式边缘人工智能，并为未来的端到端数据采集和实验验证提供了动力。
英文摘要：
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.
