w w
SOLUTIONS
, RELIABILITY ENGINEERING – A LIFE CYCLE APPROACH w w w w w w
INSTRUCTOR’S MANUAL w
CHAPTER 1 w
The Monty Hall Problem
w w w
The truth is that one increases one’s probability of winning by changing one’s choice. The
w w w w w w w w w w w w w w
easiest way to look at this from a probability point of view is to say that originally there is a
w w w w w w w w w w w w w w w w w w w w
probability of ⅓ over every door. So there is a probability of ⅓ over the door originally chosen, and
w w w w w w w w w w w w w w w w w w w
a combined probability of ⅔ over the remaining two doors. Once one of those two doors is
w w w w w w w w w w w w w w w w w
opened, there remains a probability of ⅓ over the door originally chosen, and the other
w w w w w w w w w w w w w w w
unopened door now has the probability ⅔. Hence it increases one’s probability of winning the car
w w w w w w w w w w w w w w w w
by changing one’s choice of door.
w w w w w w
This does not mean that the car is not behind the door originally chosen, only that if one were to
w w w w w w w w w w w w w w w w w w w
repeat the exercise say 100 times, then the car would be behind the first door chosen about 33
w w w w w w w w w w w w w w w w w w
times and behind the alternative choice about 66 times. Prove for yourself using Excel!
w w w w w w w w w w w w w w
Another way to prove this result is to use Bayes Theorem, which the reader can source for
w w w w w w w w w w w w w w w w
himself on the internet.
w w w w
Assignment 1.2: Failure Free Operating Period w w w w w
The FFOP (Failure Free Operating Period) is the time for which the device will run without
w w w w w w w w w w w w w w w
failure and therefore without the need for maintenance. It is the Gamma value for the
w w w w w w w w w w w w w w w
distribution. From the list of failure times 150, 190, 220, 275, 300, 350, 425, 475, the Offset is
w w w w w w w w w w w w w w w w w w
calculated as 97.42 hours – say 100 hours. This is the time for which there should be no
w w w w w w w w w w w w w w w w w w
probability of failure. It will be seen from the graph in the software with Beta = 2 that the
w w w w w w w w w w w w w w w w w w w
distribution is of almost perfect normal shape and that the distribution does not begin at the
w w w w w w w w w w w w w w w w
origin. The gap is the 100 hours that the software calculates when asked.
w w w w w w w w w w w w w
When the graph is studied for Beta = 2 it will be seen that there is a downward trajectory in the three
w w w w w w w w w w w w w w w w w w w w w
left hand points. If this trajectory is taken down to the horizontal axis it is seen to intersect it at about
w w w w w w w w w w w w w w w w w w w w w
120 hours. This is the estimation of Gamma. In the days before software this was always the
w w w w w w w w w w w w w w w w w
most unreliable estimate of a Weibull parameter and the most difficult to obtain graphically.
w w w w w w w w w w w w w w
Assignment 1.3 w
When the offset is calculated it is seen to be negative at – 185.59 (say 180). This indicates that the
w w w w w w w w w w w w w w w w w w w
distribution starts before zero on the horizontal axis. This is the phenomenon of shelf life. Some
w w w w w w w w w w w w w w w w
items have failed before being put into service. This can apply in practice to rubber components
w w w w w w w w w w w w w w w w
and paints, for example.
w w w w
1
@@SSee
isis
mmiciicsis
oolala
titoionn
,Assignment 1.4: The Choice between Two Designs of Spring w w w w w w w w
DESIGN A w DESIGN B w
Number Cycles to Failure w w Number Cycles to Failure w w
1 726044 1 529082
2 615432 2 729000
3 807863 3 650000
4 755000 4 445834
5 508000 5 343280
6 848953 6 959900
7 384558 7 730049
8 666600 8 973224
9 555201 9 258006
10 483337 10 730008
Using the WEIBULL-DR software for DESIGN A above we get
w w w w w w w w w
β=4 w w
Correlation = 0.9943 w w
F400k = 8% (measured from the graph in the Weibull printout below Fig M1.4 Set A) Hence
w w w w w w w w w w w w w w w w
R400k = 92%
w w w
For DESIGN B we get from the WEIBULL-DR software (not shown here)
w w w w w w w w w w w
Β=2 w w
Correlation = 0.9867 w w
F400k = 20% w w
Hence R400k = 80% w w w
Hence DESIGN A is better w w w w
From Fig 1.4.1 Set A we can read in the table that for F = 1% at 90% confidence, the R value is
w w w w w w w w w w w w w w w w w w w w w w
126922 cycles. For an average use of 8000 cycles per year we get 126922/8000 = 15.86 years A
w w w w w w w w w w w w w w w w w w
conservative guarantee would therefore by 15 years.
w w w w w w w
NOTE: The above calculations ignore the γ value. If this is calculated, the following figures
w w w w w w w w w w w w w w
emerge as shown in Fig 1.4.2 (the obscuration of some of the figures is the way the current
w w w w w w w w w w w w w w w w w w
version of the software prints out)
w w w w w w
DESIGN A w
β=3 w w
γ = 101 828.6 say 100 000
w w w w w w
For F = 1% at 90% confidence, F = 176149 Dividing
w w w w w w w w w w
by 8000 we get 176149/8000 = 22 years
w w w w w w w w
2
@@SSee
isis
mmiciicsis
oolala
titoionn
, Fig 1.4.1 Set A w w w
A figure of 22 years or even 15 years for any guarantee is very long indeed. Company policy
w w w w w w w w w w w w w w w w w
would have to be invoked – there are matters to consider in the determination of guarantees
w w w w w w w w w w w w w w w w
other than the test data provided. These matters could include corrosion, user abuse etc. Such
w w w w w w w w w w w w w w w
factors are more likely to occur, the longer the operating period. Questions need to be asked
w w w w w w w w w w w w w w w w
such as is there an industry standard for such guarantees, what are competitors offering as
w w w w w w w w w w w w w w w
guarantees, etc.
w w
A further point to note is that DESIGN B exhibits very peculiar characteristics if the γ value is
w w w w w w w w w w w w w w w w w
taken into account. The β value remains at 2 but the γ value is negative at over 50 000 cycles! This
w w w w w w w w w w w w w w w w w w w w w
implies that there is a probability of failure before entering service. This data looks suspect and
w w w w w w w w w w w w w w w w
further tests should be done to confirm the reliability characteristics of DESIGN B.
w w w w w w w w w w w w w
3
@@SSee
isis
mmiciicsis
oolala
titoionn