Transcript SENG 421 Reliability Demonstration Chart Department of Electrical & Computer Engineering, University of Calgary B.H.

SENG 421
Reliability Demonstration
Chart
Department of Electrical & Computer Engineering, University of Calgary
B.H. Far
（[email protected]）
http://www.enel.ucalgary.ca/People/far/Lectures/SENG421/
Reliability Demo Chart /1




An efficient way of
checking whether the
FIO (F) is met or not.
It is based on
collecting failure data
at time points.
Vertical axis: failure
number (n)
Horizontal axis:
normalized failure
data (Tn), i.e.,
failure time  F
Figure from Musa’s Book
SENG421 (Winter 2005)
[email protected]
2
Parameters Involved /1



Discrimination ratio (): Acceptable error in
estimating failure intensity.
Customer risk () : Probability that the developer
is willing to accept of falsely saying the failure
intensity objective is met (i.e., acceptance) when it
is not.
Developer risk () : Probability that the developer
is willing to accept of falsely saying the failure
intensity objective is not met (i.e., rejection) when
it is.
SENG421 (Winter 2005)
[email protected]
3
Parameters Involved /2
For  =10% and = 10% and  =2


There is 10% risk () of wrongly accepting the
software when its failure intensity objective is
actually equal or greater than twice ( =2) the
failure intensity objective.
There is 10% risk () of wrongly rejecting the
software when its failure intensity objective is
actually equal or less than half ( =2) the failure
intensity objective.
SENG421 (Winter 2005)
[email protected]
4
Reliability Demo Chart /2



1 
A  ln
B  ln
1

A changes rapidly with customer risk but very
slightly with developer risk and it determines the
intercept of accept boundary with the horizontal line
n=0
B changes rapidly with developer risk but very
slightly with customer risk and it determines the
intercept of reject boundary with the vertical line
Tn=0
SENG421 (Winter 2005)
[email protected]
5
Reliability Demo Chart /3

Boundary between accept and continue regions
A
ln 
Tn 

n
1  1 

( is the discrimination ratio)
Boundary between reject and continue regions
B
ln 
Tn 

n
1  1 
SENG421 (Winter 2005)
( is the discrimination ratio)
[email protected]
6
Reliability Demo Chart /4
Values of intercepts of boundaries with
various horizontal and vertical axes
SENG421 (Winter 2005)
[email protected]
7
Reliability Demo Chart /5
Values of A and B for various consumer and
supplier risk levels
Table from Musa’s Book
SENG421 (Winter 2005)
[email protected]
8
Reliability Demo Chart /6


When risk levels ( and ) decrease, the
system will require more test before reaching
the accept or reject regions, i.e., the continue
region becomes wider.
When discrimination ratio () decreases, the
system will require more test before reaching
the accept or reject regions, i.e., the continue
region becomes wider.
SENG421 (Winter 2005)
[email protected]
9
RDC: Example /1



Consumer risk
 = 5%
Supplier risk
 = 5%
Discrimination
ratio  = 2
Figure from Musa’s Book
SENG421 (Winter 2005)
[email protected]
10
RDC: Example /2



Consumer risk
 = 1%
Supplier risk
 = 1%
Discrimination
ratio  = 2
Figure from Musa’s Book
SENG421 (Winter 2005)
[email protected]
11
RDC: Example /3



Consumer risk
 = 0.1%
Supplier risk
 = 0.1%
Discrimination
ratio  = 2
Figure from Musa’s Book
SENG421 (Winter 2005)
[email protected]
12
RDC: Example /4



Consumer risk
 = 10%
Supplier risk
 = 10%
Discrimination
ratio  = 1.2
SENG421 (Winter 2005)
[email protected]
Figure from Musa’s Book
13
Example 1
Failure
number
Measure
(million
transactions)
Normalized
Measure
(MTTF)
1
0.1875
0.75
2
0.3125
1.25
3
1.25
5
F  4 failures/million transactions
  %10
  %10
 2
SENG421 (Winter 2005)
[email protected]
14
Example 2
Failure
number
Measure
(CPU hour)
Normalized
Measure
(MTTF)
1
8
0.8
2
19
1.9
3
60
6
F  0.1 failures/CPU hour
  0.05
  0.05
 2
SENG421 (Winter 2005)
[email protected]
15
Example 3
We are going to buy a new colour laser printer for
our department. We have borrowed the printer for
the test run and we are going to conduct
certification test on it. Maker’s data shows that we
need to change the toner every 10,000 pages. We
would like to have the system running without any
failure between the two consecutive toner changes
and in the worst case having only one failure during
the period.
a) What shall be our failure intensity objective for the
system?

F = 1/10000 pages
SENG421 (Winter 2005)
[email protected]
16
Example 3 (contd.)
b)We observe that failures occur at 4,000
pages, 6,000 pages, 10,000 pages, 11,000
pages, 12,000 pages and 15,000 pages of
output. Using the reliability demonstration
chart, what can we conclude about this
printer?
SENG421 (Winter 2005)
[email protected]
17
Example 3 (contd.)

Because of failing the certification test we will reject the
printer.
SENG421 (Winter 2005)
[email protected]
18