遥测伪周期时间序列子序列异常检测算法

Detection algorithm of abnormal sub-sequence in pseudo periodic time series of telemetry

针对现有异常检测算法用于伪周期时间序列异常序列检测时易造成误差累积,导致序列周期与特征值上显著差异的不足,文章以卫星遥测伪周期时序数据为对象,综合两种常规分段方法的优势,提出了最大周期窗宽内基于极值的模式子序列分段算法。在此基础上,给出了一种基于均序列动态生成模型的子序列异常检测方法(Anomaly Subsequence Detection method based on Optimized Sequence Model,ASD_OSM),并采用2次四分位距准则(Double Quantile ranges criterion,2Q准则)设置距离检测门限阈值,将超出阈值的序列判定为异常序列。某航天器传感器遥测子序列异常检测试验结果表明,提出的检测方法能够有效减少漏判,提高卫星遥测伪周期数据异常序列检测的准确性。

In order to detect the abnormal sub-sequence in the pseudo periodic time series of spacecraft te/emetry, a sub-sequence segmentation algorithm on the wide range of maximum cycle window was proposed based on the two conventional segmentation methods. Then, an anomaly sub-sequence detection method based on an optimized sequence model was built by using the double quantile ranges criterion to set the threshold of the distance detection. The satellite experimental results show that the method can effectively detect the abnormal subsequence of satellite telemetry data.