Quality Engineering - IM31002
Quality Engineering - IM31002
Instructions:
1. Attempt all questions
2. Make suitable assumptions if necessary
3. Maximum marks are shown against each question
4. Use statistical tables whenever required
I. Distinguish between factor, treatment, and treatment levels in the context of a health care facility.
2. Explain the importance of experimental design in quality control and improvement for a financial
institution.
3. Explain the principles of replication, randomization, and blocking, and discuss their roles in
experimental design in a semiconductor manufacturing company.
4. Explain the concept of interaction between factors, and give some examples in the entertainment
industry.
5. Explain the difference in Goal Post vis Taguchi view.
6. What is the role of a defining contrast, or generator, in fractional factorial experiments? Explain
with suitable example.
A large retail company has to del iver its goods to distributors throughout the country. It has been offered
trial-run services by three transportation companies. To test the efficiency of these three companies, it
randomly assigns its outgoing product shipments to these transporters and determines the degree of lateness
as a proportion of the time allocated for delivery. Table given below shows the degree of lateness of the
three companies for five shipments.
Question 3 [5 Marks]
A manufacturer of magnetic tapes is interested in reducing the variability of the thickness of the coating on
the tape. It is estimated that the loss to the consumer is $10 per reel if the thickness exceeds 0.005 ± 0.0004
mm. Each reel has 200 m of tape. A random sample of 10 yields the following thickness (in millimetres):
0.0048,0.0053,0.0051,0.0051,0.0052,0.0049,0.0051, 0.0047, 0.0054, and 0.0052. Find the average loss
per reel.
Page I1
- - - -- --------
Question 4 [4+3+3=10 Marks]
In the search for a lower-pollution synthetic fuel, researchers are experimenting with three different factors,
each controlled at two levels, for the processing of such a fuel. Factor A is the concentration of corn extract
at 5% and 10%, factor B is the concentration of an ethylene-based compound at 15% and 25%, and factor C
is the distillation temperature at 120°C and 150 "C. The levels of undesirable emission of the fuel are
shown in the Table given below for three replications of each treatment; each level is randomly assigned to
a treatment. The larger the level of emission, the worse the impact on the environment.
30 24 26
." 18 22 24
30 32 25
43 47 41
28 24 22
, 54 49 46
58 48 50
20 22
Your Tasks:
1. Find all ofthe main effects and the interaction effects.
2. Find the sum of squares for each of the effects and the interaction effects.
3. At the 5% level of significance, which effects are significant? Interpret your inferences.
A plant distills liquid air to produce oxygen, nitrogen, and argon. The percentage of impurity in the oxygen
is thought to be linearly related to the amount of impurities ill the air as measured by the "pollution count"
in parts per million (ppm). A sample of plant operating data is shown below:
Purity
(%) 93.3 92.0 92.4 91.7 94.0 94.6 93.6
Pollution
count
(ppm) 1.10 1.45 1.36 1.59 1.08 0.75 1.20
Purity
(%) 93.1 93.2 92.9 92.2 91.3 90.1 91.6 91.9
Pollution
count
(ppm) 0.99 0.83 1.22 1.47 1.81 2.03 1.75 1.68
Your Tasks:
1. Fit a linear regression model to the data.
2. Find a 95 percent confidence interval on ~I'
Question 6 [5 Marks]
The region of experimentation for three factors are time (40::; TI ::;80 min), temperature (200::; 12 ::;300°C),
and pressure (20::; P ::;50 psig). A first-order model in coded variables has been fit to yield data from a 23
design. The model is
Page I2