Professional Documents
Culture Documents
• If the failure rates of all failure modes of a component are constant and
independent, then the overall failure rate of the component is also constant
R(t) = exp [ -
If ƛ is constant then R(t) = e – ƛt where t ≥ 0
F(t) = 1 - R(t) = 1 - e – ƛt
f(t) = = ƛ e – ƛt
• Design Life t R
R(t R) = 0.5 = e – ƛ t R
t R= - ln R / ƛ, if R 0.5 then,
• The probability that the component will operate for next t hours is the same
regardless of whether the component is brand new, has been operating for
several hours
• Using Condition Probability
R (t I To) = R (t + To)/ R(To) = = exp (-ƛt)
• A CFR system with ƛ = 0.0004 has been operating for 1000 hrs. What is the
probability that it will fail in the next 100 hr? the next 1000 hr?
• Solution:
• If R(t) is the reliability function for the ith failure mode, assuming independence
among the failure modes, then
• System reliability is the product of these probabilities that none of thee modes occur
before time t
• System hazard rate function is the sum of the individual hazard rate of function of all
the failure modes
• ƛ s = ƛ1 + ƛ2 + ƛ3 +…….. R(t) = e - ƛ s t
ƛs =
Failure modes in bath tub includes: Burn-in, Useful Life and Wear-Out
Then we can find the reliability of the system for the mission hour
• Solution:
ƛs = 0.0003 + t / 5 x 10 5
• Components fail from switching from idle mode to operating mode like bulbs
or air-conditioners
• If constant failure rate is assumed for each failure mode and a constant
probability of failure on demand is assumed, then the component will have an
effective failure rate on a clock hour basis
• ƛi is the average failure rate when idle
• ƛo is the average failure rate while operating
• p is the probability of failure on demand
• ti is the average length of the idle time period per cycle
• to is the average length of the operating time period per cycle
• ƛ eff = i + ƛo +
ƛ eff = i + ƛo +
ƛ eff = + (1/1000) + = 0.000764
• A failed component is immediately replaced with a new one, will cause the
system to reach a steady state constant number of failures per unit of time
• For a renewal process in which failed components are replaced as they fail, a
steady state constant failure rate is obtained such that :
ƛ=
• A landing gear system has repetitive stresses placed on it twice a day as a result
of loadings. The probability of a failure during landing is 0.0028. Determine the
reliability of the landing gear system over a 30-day contingency operation. What
is the probability of a failure occurring between days 10 and 20 of the operation?
• ii. F (t) = F(b) – F(a) = R(a) – R(b) = exp (-0.0028*2*10) – exp (-0.0028*2*20)
= 0.9455 – 0.8940 = 0.0515
• Variance (1/ 2) and standard deviation (1/ƛ) of the two parameter exponential
distribution are not affected by the location parameter.
• An electronic circuit board with ƛ (t) = 0.00021 per hour is replaced on failure.
What is the probability that the third failure will occur by 10000 hours?
• Solution:
ƛ = 0.00021 ƛ t = 0.00021* 10000 = 2.1
p0= = 0.122
P1 = = 0.257
P2 == 0.270
P3 = 1- p0-p1-p2= 0.351
Two Components in Parallel: The system will fail when both the components fail
F(t) = (1- exp –ƛt) * (1- exp –ƛt) = (1- exp –ƛt) 2
ƛ(t) = =
MTTF =