A machine has three different bearings that may fail in
service.
Bearing-life distribution is in Table 2.22.
When a bearing fails, the mill stops, a repair-person is
called, and a new bearing is installed.
Cost for the bearing failures:
downtime
$5 / minute
repair-person
$15/ hour
time to change the bearing
20 minutes for one bearing,
30 minutes
for two, 40 minutes for three
bearing cost
$16/each
Table 2.24 shows the result of replacing only the broken
bearings.
Table 2.25 shows the result of the new policy: replace all
three bearings if any one is broken.
The net result is that the saving of the new policy is about
$865 a year.
Example 2.6: Random normal numbers.
A squadron of bombers attempt to destroy an anmmunition depot
(see Figure 2.8 on page 44)
If a bomb lands in an area of 600 meters (horizontal) by 300
meters (vertical) away from a specified center, it is a hit. Otherwise
it is a miss.
We use two numbers to indicate the position that a bomb hits,
X for horizontal and Y for vertical. Two separate normally distributed
random numbers are generated, one for X and the other for Y.
The result is shown in Table 2.26 on page 47.
This type of simulations doesn't involve time. They are
called Monte-Carlo, or static simulation.
