220
10 Reliability Analysis of Group III Nitride LEDs Devices
Fig. 10.8 A simplified
system failure tree
A 1
A 2
A 3
OR
A 4
AND
and arrows indicate the causal relationship between nodes. The network contains
the important conditional independence assumption. A simple Bayesian network is
showed in Fig. 10.9. In the figure, X1 X3 indicates the direct relationship between
the two variables: X1 is the parent node of X3 and X3 is the child node.
Its joint probability distribution function is.
P(x 1 , x 2 , x 3 ) = P(x 1 )P( x 2 |x 1 )P( x 3 |x 1 ).
(10.17)
Once an observation is obtained for one variable, the probability distributions of
other variables can be obtained through network updates. For example, a result of
Fig. 10.9 A simple
Bayesian Network
10 Reliability Analysis of Group III Nitride LEDs Devices
Fig. 10.8 A simplified
system failure tree
A 1
A 2
A 3
OR
A 4
AND
and arrows indicate the causal relationship between nodes. The network contains
the important conditional independence assumption. A simple Bayesian network is
showed in Fig. 10.9. In the figure, X1 X3 indicates the direct relationship between
the two variables: X1 is the parent node of X3 and X3 is the child node.
Its joint probability distribution function is.
P(x 1 , x 2 , x 3 ) = P(x 1 )P( x 2 |x 1 )P( x 3 |x 1 ).
(10.17)
Once an observation is obtained for one variable, the probability distributions of
other variables can be obtained through network updates. For example, a result of
Fig. 10.9 A simple
Bayesian Network