在航天器边缘设备上实现高效异常检测，精度高且资源消耗极低。
Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices
- 用多目标神经架构优化，将预测阈值法模型压缩至59KB内存
- 保持88.8%的异常检测准确率，计算量降低99.4%
- 适合资源受限的立方星等边缘航天器部署
航天器异常检测对任务安全至关重要，但受硬件限制，在轨部署复杂模型面临挑战。本文研究三种遥测异常检测方法——预测与阈值、直接分类、图像分类，并基于欧洲航天局异常数据集，采用多目标神经架构优化进行边缘部署优化。基线实验表明，预测与阈值法在事件级修正F0.5分数（CEF0.5）上表现最佳，达92.7%。通过帕累托最优架构优化，大幅降低计算需求：优化后模型保留88.8% CEF0.5性能，内存占用减少97.1%至仅59 KB，计算操作减少99.4%。部署可行性分析显示，优化模型仅需立方星0.36%-6.25%的内存，使在轨实时异常检测在极端资源约束下成为可能。本研究证明，复杂异常检测可成功部署于航天器边缘计算环境，实现实时响应而不越界硬件限制或影响任务安全。
原文摘要 · Abstract (English)
Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。