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.

翻译：航天器异常检测对任务安全至关重要，然而由于硬件限制，在轨部署复杂模型面临重大挑战。本文研究了三种航天器遥测异常检测方法——预测与阈值法、直接分类法和图像分类法——并利用多目标神经架构优化，针对欧洲航天局异常数据集对其在边缘部署场景下进行优化。基线实验表明，与其他方法相比，预测与阈值法取得了更优的检测性能（校正事件级F0.5分数（CEF0.5）达到92.7%）。通过帕累托最优架构优化，我们在保持性能的同时大幅降低了计算需求——优化后的预测与阈值模型将CEF0.5保持在88.8%，同时将RAM使用量减少97.1%（仅需59 KB），运算量减少99.4%。部署可行性分析显示，我们的优化模型仅需CubeSat RAM的0.36-6.25%，使得即使在高度受限的硬件上也能实现实用的在轨异常检测。本研究证明，复杂的异常检测能力可以成功部署在航天器边缘计算约束条件下，在不超出硬件限制或危及任务安全的前提下提供近乎实时的检测。