NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Using Fuzzy Clustering for Real-time Space Flight SafetyTo ensure space flight safety, it is necessary to monitor myriad sensor readings on the ground and in flight. Since a space shuttle has many sensors, monitoring data and drawing conclusions from information contained within the data in real time is challenging. The nature of the information can be critical to the success of the mission and safety of the crew and therefore, must be processed with minimal data-processing time. Data analysis algorithms could be used to synthesize sensor readings and compare data associated with normal operation with the data obtained that contain fault patterns to draw conclusions. Detecting abnormal operation during early stages in the transition from safe to unsafe operation requires a large amount of historical data that can be categorized into different classes (non-risk, risk). Even though the 40 years of shuttle flight program has accumulated volumes of historical data, these data don t comprehensively represent all possible fault patterns since fault patterns are usually unknown before the fault occurs. This paper presents a method that uses a similarity measure between fuzzy clusters to detect possible faults in real time. A clustering technique based on a fuzzy equivalence relation is used to characterize temporal data. Data collected during an initial time period are separated into clusters. These clusters are characterized by their centroids. Clusters formed during subsequent time periods are either merged with an existing cluster or added to the cluster list. The resulting list of cluster centroids, called a cluster group, characterizes the behavior of a particular set of temporal data. The degree to which new clusters formed in a subsequent time period are similar to the cluster group is characterized by a similarity measure, q. This method is applied to downlink data from Columbia flights. The results show that this technique can detect an unexpected fault that has not been present in the training data set.
Document ID
20040079350
Acquisition Source
Ames Research Center
Document Type
Conference Paper
Authors
Lee, Charles
(NASA Ames Research Center Moffett Field, CA, United States)
Haskell, Richard E.
(Oakland Univ. Rochester, MI, United States)
Hanna, Darrin
(Oakland Univ. Rochester, MI, United States)
Alena, Richard L.
(NASA Ames Research Center Moffett Field, CA, United States)
Date Acquired
August 21, 2013
Publication Date
January 1, 2004
Subject Category
Space Transportation And Safety
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
Document Inquiry

Available Downloads

There are no available downloads for this record.
No Preview Available