KEYWORDS: Failure analysis, Satellites, Amplifiers, Data modeling, Complex systems, Data analysis, Statistical analysis, Systems modeling, Control systems, Data conversion
Predicting failure in complex systems, such as satellite network systems, is a challenging
problem. A satellite earth terminal contains many components, including high-powered
amplifiers, signal converters, modems, routers, and generators, any of which may cause system
failure. The ability to estimate accurately the probability of failure of any of these components,
given the current state of the system, may help reduce the cost of operation. Probabilistic
graphical models, in particular Bayesian networks, provide a consistent framework in which to
address problems containing uncertainty and complexity. Building a Bayesian network for
failure prediction in a complex system such as a satellite earth terminal requires a large quantity
of data. Software monitoring systems have the potential to provide vast amounts of data related
to the operating state of the satellite earth terminal. Measurable nodes of the Bayesian network
correspond to states of measurable parameters in the system and unmeasurable nodes represent
failure of various components. Nodes for environmental factors are also included. A description
of Bayesian networks will be provided and a demonstration of inference on the Bayesian
network, such as the calculation of the marginal probability of failure nodes given measurements
and the maximum probability state of the system for failure diagnosis will be given. Using the
data to learn local probabilities of the network will also be covered.
KEYWORDS: Failure analysis, Satellites, Amplifiers, Data modeling, Control systems, Complex systems, Data analysis, Data conversion, Antennas, Diagnostics
Predicting failure in complex systems, such as satellite network systems, is a challenging
problem. A satellite earth terminal contains many components, such high-powered amplifiers,
signal converters, modems, routers, and generators, any of which may cause system failure. The
ability to estimate accurately the probability of failure of any of these components, given the
current state of the system, may help reduce the cost of operation. Probabilistic graphical
models, in particular Bayesian networks, provide a consistent framework in which to address
problems containing uncertainty and complexity. Measurable nodes of the Bayesian network
correspond to states of measurable parameters in the system and unmeasurable nodes represent
failure of various components. Nodes for environmental factors are also included. A description
of Bayesian networks will be provided and a demonstration of inference on the Bayesian
network, such as the calculation of the marginal probability of failure nodes given measurements
and the maximum probability state of the system for failure diagnosis will be given.
KEYWORDS: Probability theory, Data modeling, Electronic signals intelligence, Data fusion, Sensors, Decision support systems, Systems modeling, Algorithms, Data analysis, Intelligent sensors
Probabilistic graphical models, in particular Bayesian networks, provide a consistent framework
in which to address problems containing uncertainty and complexity. Probabilistic inference in
high-dimensional problems only becomes tractable when the system can be made modular by
imposing meaningful conditional independence assumptions. Bayesian networks provide a
natural way to accomplish this. As a combination of probability theory and graph theory, the
probabilistic aspects of a graphical model provide a consistent way of connecting data to models,
while graph theory provides an intuitively appealing interface to express independence
assumptions as well as efficient computation algorithms. A detailed example demonstrating
various aspects of Bayesian networks for an electronic intelligence (ELINT) sensor data fusion
decision system is presented, including a Value of Information (VOI) analysis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.