Tutorial Questions 1 Solutions

Tutorial Questions Reliability Analysis MMH131155
1. Explain the difference between the distribution of a population and the sampling
distribution of a statistic.
A sampling distribution shows how a statistic would vary with repeated random
sampling of the same size and from the same population.
2. What is Central Limit Theorem?
The central limit theorem is a justification of approximation to normality.
3. Define the term random variable and probability distribution?
Random variable: is the function that assigns a real value to every possible outcome
or event of an experiment or observation
Probability distribution: is a mathematical model that relates the value of the
variable with the probability of occurrence of that value in the population
4. What is the difference between a discrete and continuous probability distributions
5. If a random variable with probability (mass) function f(x), give an expression of the
mean, variance and standard deviation.
n
Mean X
x
i
i 1
x
n
Simple Variance S
2
i 1
(n 1)
N
Population Variance
2
x
i 1
x
n
Simple Standard Deviation S S 2
i 1
(n 1)
N
Population Standard Deviation 2
xi
i 1
6. Give an expression for the mean and variance of a continuous random variable X with
probability density function f(x).
The mean value of a continuous random variable X with probability density function
f(x):
X E( X )
x f(x) dx
The variance value of a continuous random variable X with probability density

function f(x):
X2 V ( X )
( x ) 2 f(x) dx
7. If X is a continuous random variable, for any given number a, and a < b, compute the
probability density function f(x) and cumulative distribution function F(x).
8. Give an example of 2 discrete and 2 continuous distributions frequently used in
reliability analysis and why?
9. Give the mathematical expression of the probability density function f(x) of the
following distributions
n x nx
Binomialdistribution:p(x) p (1 p) x 0,1,2,. . ,n
x
Poisson distribution : f ( x )
e x
x!
1
Normal distribution : f ( x )
2
x 0,1,....
1 ln x 2

1 2
x 2
Log - normal distribution : f (x) e

0
1 x 2

2
for (x 0)
for (x 0)
ex x 0
Exponential distribution : f (x)
0 otherwise
where - x
1 (x/)
x e x0
Weibull distribution :f ( )x
With parameter 0 and 0
0
x0
1 1 x /
x e x0
Gamma distribution : f (x) ( )

0 otherwise
10. What are the characteristics of a normal distribution

11. An aircraft landing gear has 4 tyres. Experience show that tyre burst occur on average
on 1 landing in 1200. Assuming that tyre burst occur s-independently of one another,
and that safe landing can be made if not more than 2 tyres burst, what is the
probability of an unsafe journey?
Solution
4 2 24 4 2 2 4 1 3
p(2) p 1p 0. 0 83 (0.9 17) 0. 0 83 (0.9 17)
2 2 1
n=4
p = 1/1200 =0.00083
q= (1-p) = 0.99917
The probability of a safe landing is the probability that not more than 2 tyres burst
4 0 4
0. 0 83 (0.9 17)
0
Therefore, the probability of an unsafe landing is 1-0.9999999977 = 2.310-9

12. A type of bearing has an average life of 1500h and standard deviation of 40h.
Assuming a Normal distribution determine the number of bearing in a batch of 1200
likely to fail before 1600. The bearing life distribution will therefore be
0. 0 0415970. 03 250 690.9 6 70831

0.9 9 9 7
Solution
First find the probability that an individual bearing will fail before 1600h. That is
TN(1500,40) shaded region on graph. So the upper limit of 1600 need to be
transformed
Z
t 1600 1500
2. 5
40
Z = 2.5 Table value gives 0.4938, that is ( 2.5) 0.4938

P(T 1600) = 0.5 + 0.4938 = 0.9938
From a sample of 1200 we can expect (12000.9938) = 1192.56 to fail
13. The lifetime of a population (100) of a lip seal is assumed to follow an exponential
distribution with hazard rate of 0.02 failures per year. What is the probability of the
seal failing 3 years?
Solutions
F (t ) exp(t )
0.02 failures per year
F(3 years) = 1 exp(-0.023) = 1 exp(-0.06) = 1- 0.94 = 0.06

For a population of 100 similar seals, the expectation is that 6 out of 100 would fail
during the 3 years period.
14. The measurement of the diameter of a random sample of 200 ball bearings made by a
certain machine during 1 week showed a mean of 8.24 mm and a standard deviation
of 0.42 mm
Find (a) the 99% and (b) the 95% confidence interval for the mean diameter of all the
ball bearings
Solutions
(a). X 1.96 X 1.96 s 8.24 1.96 0.42 8.24 0.058mm
N
N
200
(b). X 2.58 X 2.58s 8.24 2.58 0.42 8.24 0.077 mm
N
N
200
or
8.24 0.06mm
or
8.24 0.08mm
15. Derive an expression for the joint probability density function and show its relation in
calculating the maximum likelihood estimator.
16. Show how you can analytically estimate the parameter of an exponential distribution
using the maximum likelihood estimator.
17. In an attempt to establish the repair time probability distribution, and engineer
obtained the following times, in hours, to restore a failed machine
3.0
3.8
0.5
10.0 2.4
1.5
0.6
4.3
3.0
1.2
1.8
2.8
(i). Compute the sample mean and determine the 90 percent confidence interval for
the MTTR
(ii) Determine the best distribution (using probability plots)
(iii) On the basis of the distribution, is maintainability objective of 90 percent of the
repairs completed in 3 hours being met?
18. Determine whether the following complete data came from an exponential
distribution
396
391
401
389
346
343
390
425
360
380
413
437
481
408
413
414
392
374
433
402
435
362
372
354
434
19. What are the different types of censoring use in reliability data analysis?
20. Statistical analysis of the reliability data is used to select an ideal distribution. What
are the necessary steps that could be used in identifying appropriate distributions for a
given reliability date set.
21. What is the difference between right and left censored data give examples?
22. Define the term failure modes and mention how you can classify failure modes in
reliability analysis of complex systems?
23. Derive the function form of the hazard function of a system using multiplicative laws
of probability.
24. Discuss how you can distinguish the pattern of failure for a repairable and nonrepairable system.
25. In reliability analysis of system, discuss the importance of using the bathtub curve and
establish its relation to hazard rate function.
26. Give the functional form of the density, reliability and hazard function of an extreme
value Weibull distribution.
27. The value of the Weibull shape parameter provides insight about the behaviour of the
failure process. Discuss the properties considering the variety of shapes that are
obtainable.
28. What is a stochastic process?
29. Give an expression of the intensity function of a stochastic point process.
30. In reliability modelling, stochastic point process models are used. Mention the two
types of point process models and discuss their characteristics.
31. What are competing risks and how does it relate to equipment reliability. Give an
expression showing the frame work of the competing risk model in term of the subsurvival function and conditional probabilities

Tutorial Questions 1 Solutions

Uploaded by

Copyright:

Available Formats

Tutorial Questions 1 Solutions

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Tutorial Questions 1 Solutions

Uploaded by

Copyright:

Available Formats

Tutorial Questions Reliability Analysis MMH131155

Simple Standard Deviation S S 2

Population Standard Deviation 2

The variance value of a continuous random variable X with probability density

Log - normal distribution : f (x) e

Gamma distribution : f (x) ( )

10. What are the characteristics of a normal distribution

Therefore, the probability of an unsafe landing is 1-0.9999999977 = 2.310-9

0. 0 0415970. 03 250 690.9 6 70831

Z = 2.5 Table value gives 0.4938, that is ( 2.5) 0.4938

0.02 failures per year

F(3 years) = 1 exp(-0.023) = 1 exp(-0.06) = 1- 0.94 = 0.06

You might also like