figure 4. a reliability block diagram (top), with a systematic method for mapping its blocks
into Bayesian network fragments (bottom).
picted in the table here as an example.
figure 5. a Bayesian network generated automatically from a reliability block diagram.
Fan 1 (F1)
Processor 1 (P1)
variables E, F1, F2, P1, P2 and D represent
the availability of corresponding components,
and variable S represents the availability
of the whole system. variables Ai correspond
to logical ands, and variables Oi correspond
to logical ors.
Fan 2 (F2)
Processor 2 (P2)
For example, in many applications
that involve system analysis, such as
reliability and diagnosis, one can syn-
thesize a Bayesian network automati-
cally from a formal system design.
Figure 4 depicts a reliability block dia-
gram (RBD) used in reliability analysis.
The RBD depicts system components
and the dependencies between their
availability. For example, Processor 1
requires either of the fans for its avail-
ability, and each of the fans requires
power for its availability. The goal here
is to compute the overall reliability
of the system (probability of its avail-
ability) given the reliabilities of each
of its components. Figure 4 shows also
how one may systematically convert
each block in an RBD into a Bayes-
ian network fragment, while Figure 5
depicts the corresponding Bayesian
network constructed according to this
method. The CPTs of this figure can be
completely constructed based on the
reliabilities of individual components
(not shown here) and the semantics of
the transformation method. 8