Promblem with mapping fault tree into bayesian network on GeNIe

The front end.
Post Reply
Poriteslutea
Posts: 1
Joined: Fri Jul 29, 2022 9:22 am

Promblem with mapping fault tree into bayesian network on GeNIe

Post by Poriteslutea »

Hi, I want to map a fault tree into bayesian network on GeNIe, but I got wrong posterior probability after updating.

The fault tree is like that:
Image

I gave the probability of basic events (a, b, c) and conditional probability table of intermediate events(E1, E2) and top event.
The conditional probability table for 「or」logic gate is like that:
Image

And here is the result after mapping into bayesian network and updating:
Image

I supposed the probability of 'TOP' event is:
False: 40.8% (60% * 68% TOP is false only when both E1 and E2 are false )
True: 59.2%
The result calculated by GeNIe is "True:46%, False:54%" of TOP event, which was different with what I calculated.
However, the results of E1 and E2 don't have this problem, the results of posterior probability are the same as which I calculated by myself.

This situation only occurred when different child nodes have common parent node on bayesian network(ex. b to E1 and E2) , but I really don't understand why... Hope someone can help me, thanks!
marek [BayesFusion]
Site Admin
Posts: 430
Joined: Tue Dec 11, 2007 4:24 pm

Re: Promblem with mapping fault tree into bayesian network on GeNIe

Post by marek [BayesFusion] »

Your error is assuming that E1 and E2 are independent. They are not, as they have a common ancestor, b. Because they are dependent, you cannot just multiply probabilities as you did in your calculation.

I hope this helps,

Marek
Post Reply