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极具挑战性，原因在于故障稀疏、具有时间结构化特征，且分布在异构的PX4遥测流中，这些遥测流可能伴随传感器可用性变化及数值缺失。我们提出了AeroTSBoost——一个面向真实世界无人机遥测异常挖掘的时间-统计提升框架。AeroTSBoost通过对齐多元飞行日志，将每个时间窗口转换为确定性描述符，以捕捉分布偏移、分位数结构、端点漂移、局部动力学和滞后相关性，并训练一个类别平衡的LightGBM检测器。在UAV-SEAD数据集上，AeroTSBoost在评估的经典方法、有监督表格方法、神经重建方法、循环方法、基于Granger因果关系的方法及频域基线方法中取得了最强的AUPRC指标。在五组随机种子下，其AUPRC达到$0.7516\pm0.0043$，阈值扫描事件F1达到$0.5342\pm0.0108$，相较于非AeroTSBoost最优基线，AUPRC绝对提升了5.79个百分点。在时序净化和逐日志留出协议下，AeroTSBoost仍保持最优AUPRC性能，分别达到$0.6066\pm0.0193$和$0.6388\pm0.0315$。在相关ALFA固定翼无人机故障日志上，AeroTSBoost的逐序列留出AUPRC达到$0.9259\pm0.0076$，优于随机森林（$0.8835\pm0.0797$）和仅矩特征方法（$0.8700\pm0.0481$）。这些结果表明，在运营级信息物理遥测数据的稀疏异常挖掘任务中，确定性时间-统计表征方法仍具有极强的竞争力。