search

jieunbyun / BNS-JT

Reference: Byun, J.-E. and Song, J. (2021). A general framework of Bayesian network for system reliability analysis using junction tree. Reliability Engineering & System Safety, 216, 107952.
MIT License
5 stars 4 forks source link

output of fnTrans.doBranch #9

Closed dynaryu closed 1 year ago

dynaryu commented 1 year ago

For node 5 to 1 

Input:
arc_paths = [[2], [1, 3]]
path_times = [0.0901, 0.2401]
unfinished = 0

Output:
branches_surv = [[2], [1, 3], [1], []]
branches_fail = [[], [2], [2, 3], [1, 2]]
states = [1, 2, 3, 3]
times = [0.0901, 0.2401, 100, 100]

Why state of the second case (arc [1, 3] survival, arc [2] failure) becomes 2 not 1? What does 1, 2, and 3 mean as a system for this case?

jieunbyun commented 1 year ago

Because the states are defined by the travel time, and it takes different times to travel by arc 2 and by arc 1 & 3. The array “times” illustrates the corresponding travel times to each state.

From: Hyeuk Ryu @.> Sent: 31 March 2023 11:41 To: jieunbyun/BNS-JT @.> Cc: Subscribed @.***> Subject: [jieunbyun/BNS-JT] output of fnTrans.doBranch (Issue #9)

For node 5 to 1

Input:

arc_paths = [[2], [1, 3]]

path_times = [0.0901, 0.2401]

unfinished = 0

Output:

branches_surv = [[2], [1, 3], [1], []]

branches_fail = [[], [2], [2, 3], [1, 2]]

states = [1, 2, 3, 3]

times = [0.0901, 0.2401, 100, 100]

Why state of the second case (arc [1, 3] survival, arc [2] failure) becomes 2 not 1? What does 1, 2, and 3 mean as a system for this case?

— Reply to this email directly, view it on GitHubhttps://github.com/jieunbyun/BNS-JT/issues/9, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AFIK4XYWLEKQM3O3QROFC5TW62YD3ANCNFSM6AAAAAAWOPJ2XI. You are receiving this because you are subscribed to this thread.Message ID: @.**@.>>

dynaryu commented 1 year ago

What I said last night was some potential issue due to too many states from continuous variable. Alternative approach is binning which converts continous variable to categorical one.

jieunbyun commented 1 year ago

Thanks, I will keep that in mind and think over.

From: Hyeuk Ryu @.> Sent: 06 April 2023 01:34 To: jieunbyun/BNS-JT @.> Cc: Ji-Eun Byun @.>; Comment @.> Subject: Re: [jieunbyun/BNS-JT] output of fnTrans.doBranch (Issue #9)

What I said last night was some potential issue due to too many states from continuous variable. Alternative approach is binning which converts continous variable to categorical one.

— Reply to this email directly, view it on GitHubhttps://github.com/jieunbyun/BNS-JT/issues/9#issuecomment-1498335179, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AFIK4X46R2GLXQ5T3KCUJO3W7YFOTANCNFSM6AAAAAAWOPJ2XI. You are receiving this because you commented.Message ID: @.**@.>>