ADDIS ABABA UNIVERSITY

ADDIS ABABA INSTITUTE OF TECHNOLOGY

SCHOOL OF MECHANICAL AND INDUSTRIAL
ENGINEERING
RELIABILITY ENGINEERING
(MIEng-6572)
Assignment On:
Chapter 5 Assignment 5: Reliability Tests

SUBMITTED BY:
Abraham Tilahun
ID No: GSE/6950/13

SUBMITTED TO:
Dr. Kassu Jilcha (Asst. Prof.)
Jun 1, 2023
Addis Ababa, Ethiopia
Part I’ Discussion Type Questions
1. There are numbers of factors those affect reliability tests. Which factors affect the
reliability of test? List outthem.

Answer
1. The Length of the test,
2.  !he expression of the items in the test
3. Homogeneity of the group
4. !he duration of the test
5. Objectivity in scoring
6. !he conditions in making a measurement
7. !he explanation of the test
8. The Characteristics of the items of the test
9. Difficult# of the test
2. Can a test produce scores that are reliable but not valid? Explain briefly why or why not.

Answer
YES: because
A measure can be reliable but not valid, if it is measuring something very consistently
but is consistently measuring the wrong construct.
Example:
3. Can a test produce scores that are valid but not reliable? Explain briefly why or whynot.
Answer
YES: because
A measure can be valid but not reliable if it is measuring the right construct, but not
doing so in a consistent manner. Like from the above example en Q2.

4. State whether the following statements are true orfalse.

a. The objective of reliability life testing is to obtain informationaboutfailuresin
order to quantify and improve productreliability. True
b. Binomial testing results in a reliability demonstration that will discriminate
between an acceptable and unacceptable reliability at specified risklevels.
True
c. When failures are accelerated mainly as a result of an increase in temperature,
Arrhenius model is thebest. True

5. Match the correct statements in columns A andB.

Column “A” Column
“B”
1. Burn-in and screentest=c a) Test to reduce the length of test by
2. Sequentialtest=d accelerating failures
3. Acceptance and b) Statistical test to isolate the causes offailures
qualificationtest=e c) Test to eliminate the infantmortality
4. Experimentaldesign=b d) Test to demonstrate that the reliability/
5. Accelerated lifetest= a maintainability goal are met or notmet
e) Testto demonstrate thatthe reliabilitygoals
have been met, parts and components are
withinacceptable Limits.

6. The wear out failure modes, such as corrosion and cracking, of a motor can be
accelerated by operating the system under increased temperature, humidity and in
presence of a catalyst. If the failure of motor follows an exponential model, how will
you estimate the mean time to failure at normal operating condition, by knowing the
MTTF under acceleratedconditions?
Answer
Given: Failure rate = number of failures/total uptime
MTTF @ an accelerated condition = T/r where T= cumulative test time and r= total
 number of failures
MTTF @ an exponential model = 1/µ, where µ is the mean failure rate
Required: MTTF @normal condition=?
Mean time to failures is the average – or mean time that elapses from one unplanned
breakdown to the next, under normal operating conditions.

MTTF (under normal condition) = AF* MTTF (under accelerated condition)

= AF* 1/ µ (under accelerated condition)

7. A centrifugal pump used in a refinery follows a Weibull reliability model. How to

estimate the required burn-in period for the pump? How to ascertain to what degree
the burn-in testing is to beutilized?

Answer
By examining the slope of the Weibull probability distribution we can decide to what degree
the burn-in test should be utilized. Hence there are four different cases
Case 1: Systems with increasing failure rate
Systems of this kind are already in their wear out stage from the start time. In this case, burn-
in will have a negative effect. It would make the systems worse, because systems that do
survive the burn-in will have a greater failure rate than what they had before the test and will
be more likely to fail in the field. Performing a burn-in is not advised in this case.
Case 2: Systems with decreasing failure rate
Systems with decreasing failure rates are ideal candidates for burn-in testing. For such
systems, longer burn-in periods will result in surviving systems that are better than new
systems, but will also result in more discarded weak systems. The burn-in period should be
determined based on a certain criterion (for example, optimizing burn-in time based on a
reliability goal, a failure rate goal or cost of burn-in and future replacements).

Case 3: Systems with bathtub failure rate

In this case we consider that the system follows a period of decreasing failure rate, followed
by an increasing failure rate period (and possibly an intermediary constant failure rate
period). Note that the term bathtub curve is usually used to describe an entire non-
homogeneous population of units. Here, however, we are using it to describe the failure rate
of a single system or each system in a population of systems. We can determine the
appropriate burn-in time for the system that could eliminate the early life problems.
Case 4: System with constant failure rate
for such systems, burn-in makes the population neither better nor worse. In these cases, burn-
in is not recommended because it would be a strategy that is useless and will only result in
increased costs and delays.

8. In industry, statistical tests are extensively used for product quality testing. Do you
know, what is the criterion to accept or reject a null hypothesis?
Answer
The following steps are performed to reject or accept the null hypothesis
Step 1: State the null hypothesis and the alternative hypothesis
Step 2: find the calculated critical value
Step 3: find the critical value from the table
Step 4: Compare the calculated value from the critical value of the table
Step 5: if the calculated value in step 2 is > the critical value in step 3, then reject the
null hypothesis

9. For material subjects to corrosion, the length of time before degradation become
unacceptable is being lengthy. If you know the corrosion rate and the maximum
allowable loss, after which the material is no longer structurally sound, how will you
estimate the time to failure? (Corrosion rate measures the thickness loss of material
per unit oftime)
Answer:
Given:
 Corrosion rate
 Upper(maximum limit)
Required:
Time to failure=?
g(x )=d-CR.t
d = maximum allowable corrosion depth
CR = corrosion rate
t = duration of wet service
X¯= vector containing all the basic uncertainty variables
 l
v
e
D
m
I
g
s
y
A
&
p
c
n
o
i
t
u
a
E
10. Try to discuss and illustrate by example the stages of system lifecycle?

• Analysis-The analysis stage includes gathering all the specific details required for a new
system as well as determining the first ideas for prototypes.
• Design-The design stage is a necessary precursor to the main developer
stage.Developers will first outline the details for the overall application, alongside
specific aspects, such as its:
 User interfaces
 System interfaces
 Network and network requirements
 Databases
• Development &testing-The development stage is the part where developers actually
write code and build the application according to the earlier design documents and
outlined specifications.Implementation- it must be tested to make sure that there
aren’t any bugs and that the end-user experience will not negatively be affected at any
point.

During the testing stage, developers will go over their software with a fine-tooth comb,
noting any bugs or defects that need to be tracked, fixed, and later retested.
• Documentation-Documentation is any communicable material that is used to describe,
explain or instruct regarding some attributes of an object, system or procedure, such
as its parts, assembly, installation, maintenance and use
• Evaluation-measuring the final system against its initial performance goals as well as
performing ongoing testing to see that the system continues to meet those goals.
11. Discuss the product testing types, reliability life testing and factors to be considered in
reliability testing?

 Product testing types

 Functional Or Operational Tests -To test the performance requirements and to

evaluate design adequacy Environmental Stress Test -For testing the capability of
product to survive at various operating conditions.

 Reliability Qualification Test -To measure product reliability

 Safety Test -To find hazards ,catastrophic occurrences ,loss of life or economic loss
by generating faulty actions.

 Reliability Growth Testing -Consists of reliability testing of prototypes through’

which the causes for failure is found and those failures are eliminated by design
modification
 Reliability life testing is Reliability or life testing involves estimating the
expected durability over time of an item. This may be an entire system, a
product, or an individual component. And may also focus on an element of a
component, such has a material property. It also provide information for entire life
about maintenance plan corrective actions on design and process for a tested product

 Factors to be considered in reliability testing;

o Objective of the test

o Type of test to be performed

o Operating and environmental conditions.

o Number of units to be tested(sample size)

o Duration of test

o Unequivocal definition of failure

12. Discuss test stages and test methods inreliability?
Reliability Test stages
1. Infant stage -ability to fulfill the need
2. Development stage -performance, reliability, cost and modes of behavior
3. Evolution stage - compare to improve economy, maintenance and use of standard
parts
4. Performance stage - requirements of performance and reliability
 5. User stage - withstand handling, transportation etc.
Reliability Test methods
 Marginal testing-It is prescribed by designer.
 Nondestructive testing.-involves comparing a known input to a measured output and
comparing to a known model - does not require the sacrifice of the physical system, as would
be the case with disassembly, dissection, or failure testing
 Destructive testing. -is most suitable, and economical for objects which will be mass
produced, as the cost of destroying a small number of specimens is negligible.
 Accelerated testing-is the process of testing a product by subjecting it to conditions (stress,
strain, temperatures, voltage, vibration rate, pressure etc.) in excess of its normal service
parameters in an effort to uncover faults and potential modes of failure in a short amount of
time.
 Burn-in and screen testing-is an accepted practice for detecting early failures in a
population of semiconductor devices. Its objective is to eliminate or reduce “infant morality
“failures by accumulating initial operating hours and resulting failures prior to user
acceptance.
 Acceptance and qualification testing- is a quality assurance (QA) process that determines
to what degree an application meets end users' approval.
 Sequential testing-provides a more efficient method to verify equipment reliability
achievement
 Experimental design-means planning a set of procedures to investigate a relationship
between variables. To design a controlled experiment, you need: A testable hypothesis.

Part II: Workout Type Questions

1. During a testing cycle, 20 units were tested for 50 hr with the following failuretimes
and censor times observed: 10.8, 12.6+, 15.7, 28.1, 30.5, 36.0+, 42.1, 48.2.Determine
the total test time and estimate the MTTF for this particular cycle, assumingCFR.

Solution:

n
TypeI multiply: =∑ ti+ ( n−r−k ) t∗¿
ti=1

whwer :

n = nbr on test k = nbr multiplycensors

r = nbr failures ti= failure time

 ti+= censor time tr= test time (Type II)

t*= test time (Type I)

MTTF = T / r

Given

t*= test time (Type I)=50

n = nbr on test=20

k = nbr multiplycensors=2

r = nbr failures=8-2=6

So the

n
TypeI multiply: =∑ ti+ ( n−r−k ) t∗¿
ti=1

For Type I testing T=10.8 + 12.6 + 15.7 + 28.1 + 30.5 + 36.0 + 42.1+48.2 + (20 - 6 -
2) 50

= 824 hours

ThenMTTF = 824/6 = 137.3 hours.

2. To support the current cycle in a reliability growth testing program, a total of 8
failures need to be generated. The current estimate of the MTTF is 55 hr. the test
department is scheduled to complete testing within 72 hr. How many units should be
placed on test? If the test department is told it must complete, the testing within 48 hr.,
how many failures would it expect togenerate
Solution:
MTTF=55 hr.
E=72 hr.
E( test time)= MTTF x TTFr,n
TTFr,n= MTTF/E

This is Type II testing. Since the length of test is MTTF *TTFr, nthen,
TTF8, n=72 /55=1.31

 From the standard table,

 TTF8, 10=1.429
TTF8, 11=1.187

Then, 11 units should be placed on test.

 Then If the test department is told it must complete, the testing within 48 hr., how
many failures would it expect togenerate
E=48 hr.
r=?

 TTFr, 11 = 48 /55=0.872
So TTF7, 11=0.937
TTF6, 11 =0.737
Then the failure is 6 units
3. The reliability testing has shown that a ground power unit used to supply DC power
to aircraft has a Weibull distribution with β= 0.5.0 and α= 45000 operating hours.
Determine burn- in period necessary to obtain a required reliability specification of
R(1000)=0.90.
Solution:
First of all checked weather it is necessary y to find the bur in period that means
R(1000)=e(1000/45000)0.5=0.89 <1
And then β<1 Therefore, the burn-period is necessary. Numerically solving
¿¿
(𝑡|𝑇0)= e =0.90

ln0.90=(−(1000+T ¿ ¿ 45000)) 0.5+( 4500

T
) 0.5 ¿
-0.105=(−(1000+T ¿ ¿ 45000)) 0.5+(
4500 )
T
0.5 ¿

T= 126 hr.
Then R (1000/126)=0.90
4. Test thehypothesis
H0 :R0= 0.90
H1:R1= 0.85.0
With α= 0.05 and β= 0.10
Solution:
R0=0.90 R1=0.85 α=0.05 β=0.10
A= = 0.1/(1-0.05)= 0. 10526
B= (1-0.1)/0.05=18
D= ln[(R0(1-R1)/(R0(1-R1)]=ln[(0.85(1-0.90)/(0.90(1-0.85)]=-0.4626
 Slope of the accept/reject lines is,  ln( 0.15/0.10)/ D  0.876
Then, ln(B /) D-0.6 2478 and ln(A /) D = 4 .866 . The acceptance region is - 6.2478 +
0.876n < yn < 4.866 +0.876n and H0 will be rejected if ynfalls below the lower
bounds, and accepted if ynexceeds the upper bound. A graph of the regions is shown
below. The minimum number of test cases to reject H0is 8 (where the reject line first
crosses the horizontal axis),whereas the minimum number needed to accept H0is 40.
Below 40, the number of survivors needed to accept H0 is more than the number at risk.
5. An automotive part was tested at an accelerated cycling level of 100 cycles per hour.
The resulting failure data were found to have a Weibull distribution, with β= 5.2 and

α= 1000hrs. If the normal cycle time is 5 per hour, what is the normal cycle
characteristic life andreliability?

Solution:

β= 5.2 and α= 1000hrs

xa=100/hr.= accelerated cycle

xn=5/hr.= normalcycle

Then what is the normal cycle characteristic life andreliability=?

let say αn=normal cycle =?

Rn(t)=reliability in the normal cyle

Xα
αn= a= (100/5)*1000
xn

=20000hr.

Then reliability Rn(t)=?

( )
β
t
Rn(t)= e−
αn

=e [-(t/20000)5.2] =
But there is no given time
6. An electronic component has a normal operating temperature of 294 K (about 21 0C).
Under stress testing at 430K a Weibull distribution was obtained with ɵ=
254hrs, and at 450k, a Weibull distribution was obtained with ɵ= 183hrs.The shape
parameter didn’t change with β=1.72. Compute the acceleration factor to be applied at
 the normal stress temperature. What is the characteristic life at normal
operatingtemperature?
Solution:
Arrhenius equation (for reliability)
AF= exp [(Eaa/k) (1/T1 - 1/T2)]
Eaa =is the apparent activation energy (eV)
AF= acceleration factor
Therefore, the acceleration factor to be applied at the normal stress temperature,
T1=430k ,T2=450k ,ϴ1=254hrs. ,ϴ2=183hrs.
Eaa is the apparent activation energy (eV)=
254
lnAF ln ⁡( )
183
Eaa=
( 1
−
T1 T2
1
)= ( 1
−
1
430 450 )
=3172

AF= e(3172) (1/430 - 1/450)]=1.387

Therefore, the time to failure of the component at normal temperatures is
estimated to be Weibull with a shape parameter didn’t change of 1.72
ϴ=1.387xϴ2=253.8 hrs.
7. Background: A communication system has minimum acceptable value (MAV) of
100 hrs.
MTBF,andaspecifiedvalue(SV)of150hrs.MTBF.Determine:Howmanyhoursoftestare
required for design qualification prior to a production decision if we desire α and β risks of
10% each?
Solution:

Given:
ϴ1=100
ϴ0=150
α=0.1
β=0.1
d=150/100=1.5
8. For constant failure rate (CFR) model mean time to failure was found to be 235hrs and the
cumulative test time was given as 55 hours for the total test number of 500units.
a. What was the total numbers of failures in this test timelength?
b. What is expected mean time tofailure?
c. Whatisthetestfactortime(TTRr,500)?
d. What is the estimated test time if failure units are replaced and r units are there ontest?

Solution:
MTTF=235 hr.
T=55 hr.
n=500 units
a) MTTF= T/r
r= T / MTTF =55/235
=0.23
b) E
c) (TTRr,500)=?
E(test time)=MTTF x TTRr,n,
TTRr,500) =MTTF/E= 235/0.108=2,175.92
d) =E(test time)=MTTF* (r/n) 235/(0.23/500)= 0.108 hr.