Abstract
This paper discusses a mixed method that combines unsupervised learning methods and human expert input for analyzing telemetry data from long-duration robotic space missions. Our goal is to develop more automated methods for detecting anomalies in time series data. Once anomalies are identified using unsupervised learning methods we use feature selection methods followed by expert input to derive the knowledge required for building on-line detectors. These detectors can be used in later phases of the current mission and in future missions for improving operations and overall safety of the mission. Whereas the primary focus in this paper is on developing data-driven anomaly detection methods, we also present a computational platform for data mining and analytics that can operate on historical data offline, as well as incoming telemetry data on-line.
Highlights
As engineered systems have become more complex, selfmonitoring, self-diagnosis, and adaptability to maintain operability and safety have become focus areas for research and development
We have developed a mixed anomaly detection method that combine unsupervised learning methods combined with human-expert support to analyze telemetry data from spacecraft missions
We have described the various steps of the method from the data pre-processing, generation of the feature space, applying a clustering algorithm, determining nominal and outlier processes, associating significant features with the outlier groups, to the consultation with experts resulting in the identification and characterization of special modes of operation as well as anomalous behavior of the system
Summary
As engineered systems have become more complex, selfmonitoring, self-diagnosis, and adaptability to maintain operability and safety have become focus areas for research and development. The longer-term goal is to develop Cyber Physical Systems (CPSs) Lee (2008); Marwedel (2010); Niggemann et al (2015) that can monitor their own behavior, recognize unusual situations, and inform operators, who can modify system operations to ensure safety and ability to complete a mission. In some situations, this information can help to plan maintenance tasks. Simplified Block Diagram INTERNATIONAL JOURNAL OF PROGNOSTICS AND HEALTH MANAGEMENT
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
