用统计方法优化LSTM异常检测标签，提升火箭推进系统故障识别精度。
Time-Series Anomaly Classification for Launch Vehicle Propulsion Systems: Fast Statistical Detectors Enhancing LSTM Accuracy and Data Quality
- 基于马氏距离和正反向检测比例设计新统计判别器
- 使LSTM分类器精确率提升7%，召回率提升22%
- 适用于新火箭型号的故障预警，减少人工判断误差
发射前的决策需实时评估遥测数据是否超出设计阶段设定的红线阈值。以往常依赖地面测试或历史飞行数据识别初始故障模式及其发生时间，但该方法严重依赖工程经验，对新型运载火箭更易出错。为此，本文采用长短期记忆（LSTM）网络进行时序异常的有监督分类。然而，基于仿真异常数据生成的初始训练标签可能因异常强度、稳定时间等因素存在偏差。本文提出一种基于马氏距离与正向/反向检测比例的新统计判别器，用于重标注训练数据。在单次运行长达20.8分钟、总计约10^8个训练时间步的推进系统数字孪生仿真中，该方法使LSTM分类器的精确率提升7%，召回率提升22%。
原文摘要 · Abstract (English)
Supporting Go/No-Go decisions prior to launch requires assessing real-time telemetry data against redline limits established during the design qualification phase. Family data from ground testing or previous flights is commonly used to detect initiating failure modes and their timing; however, this approach relies heavily on engineering judgment and is more error-prone for new launch vehicles. To address these limitations, we utilize Long-Term Short-Term Memory (LSTM) networks for supervised classification of time-series anomalies. Although, initial training labels derived from simulated anomaly data may be suboptimal due to variations in anomaly strength, anomaly settling times, and other factors. In this work, we propose a novel statistical detector based on the Mahalanobis distance and forward-backward detection fractions to adjust the supervised training labels. We demonstrate our method on digital twin simulations of a ground-stage propulsion system with 20.8 minutes of operation per trial and O(10^8) training timesteps. The statistical data relabeling improved precision and recall of the LSTM classifier by 7% and 22% respectively.
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。