Intelligent pattern analysis and anomaly detection of satellite telemetry series with improved time series representation

Telemetry data, sent by the satellite, is the only basis for ground staffs to monitor on-board equipment status. In addition, the pattern discovery and operating state identification of telemetry data are very essential for automatic anomaly detection and problem diagnosis for satellites. Clustering, as an important data mining method for time series, can realize pattern discovery of satellite telemetry data automatically and intelligently, whereas the large amount of raw data and pseudo-period characteristic make the clustering on raw data inefficient and susceptible to noise interference. Thus, based on the prominent shape features and Time-Spatial specialty, a clustering framework is proposed for telemetry data mining with physical-based segmentation and improved time series representation. Moreover, different distance measures are introduced to this framework to realize the time series clustering. The experiments are firstly performed on the public data sets which have high similarity with the real satellite telemetry to quantify the clustering accuracy, then a case study on the real satellite telemetry verifies the effectiveness and applicability of the proposed framework.