Mining anomalies from unmanned aerial vehicle (UAV) state-estimation logs is challenging because failures are sparse, temporally structured, and distributed across heterogeneous PX4 telemetry streams with variable sensor availability and missing values. We present AeroTSBoost, a temporal-statistical boosting framework for real-world UAV telemetry anomaly mining. AeroTSBoost aligns multivariate flight logs, converts each window into deterministic descriptors that capture distributional shifts, quantile structure, endpoint drift, local dynamics, and lag correlation, and trains a class-balanced LightGBM detector. On UAV-SEAD, AeroTSBoost achieves the strongest AUPRC among evaluated classical, supervised tabular, neural reconstruction, recurrent, Granger-causality-based, and frequency-domain baselines. Across five seeds, it reaches $0.7516\pm0.0043$ AUPRC and $0.5342\pm0.0108$ threshold-swept event F1, improving AUPRC by 5.79 absolute points over the strongest non-AeroTSBoost baseline. Under purged chronological and leave-log-out protocols, it remains the best AUPRC method, reaching $0.6066\pm0.0193$ and $0.6388\pm0.0315$, respectively. On related ALFA fixed-wing UAV fault logs, AeroTSBoost reaches $0.9259\pm0.0076$ leave-sequence-out AUPRC, ahead of RandomForest ($0.8835\pm0.0797$) and moments-only ($0.8700\pm0.0481$). These results show that deterministic temporal-statistical representations remain highly competitive for sparse anomaly mining in operational cyber-physical telemetry.

翻译：从无人机状态估计日志中挖掘异常具有挑战性，因为故障具有稀疏性、时间结构性，并分布在异构的PX4遥测流中，且伴随传感器可用性变化与缺失值。我们提出AeroTSBoost，一个面向真实世界无人机遥测异常挖掘的时间-统计增强框架。AeroTSBoost对齐多变量飞行日志，将每个时间窗口转换为确定性描述符，捕捉分布偏移、分位数结构、端点漂移、局部动力学与滞后相关性，并训练一个类平衡的LightGBM检测器。在UAV-SEAD数据集上，AeroTSBoost在所有评估的经典方法、监督式表格方法、神经重建方法、循环方法、基于Granger因果关系的方法以及频域基线上取得了最强的AUPRC。在五次随机种子下，其达到$0.7516\pm0.0043$ AUPRC和$0.5342\pm0.0108$阈值扫描事件F1值，相较于最强非AeroTSBoost基线提升AUPRC绝对5.79个百分点。在纯净时间序列与留日志交叉验证协议下，它仍为最优AUPRC方法，分别达到$0.6066\pm0.0193$与$0.6388\pm0.0315$。在相关的ALFA固定翼无人机故障日志上，AeroTSBoost达到$0.9259\pm0.0076$留序列交叉验证AUPRC，优于RandomForest（$0.8835\pm0.0797$）与仅使用矩特征的方法（$0.8700\pm0.0481$）。这些结果表明，确定性时间-统计表征在运行信息物理遥测系统的稀疏异常挖掘中仍具高度竞争力。