You are on page 1of 16

Remove Watermark Wondershare

PDFelement

Indian Institute of Technology, Kharagpur


Department of Industrial and Systems Engineering

QDC Laboratory (IM39005)

Experiment No. 6

Group No. :4

Group Members: Himanshu Anand -21IM10014


Ketaki Mali-21IM10015
Pahnabi Roy-21IM10018
Pankaj Sharma-21IM10019

Date of Experiment/Data Collection: 9/10/23

Date of Submission: 16/10/23

Experiment Number:6

Title of the Experiment: Simulation Studies on Acceptance Sampling (Single Sampling)

Objectives of the Study: The basic objective is to know the general nature and
characteristics of the experimental OC and AOQ curve in relation to those obtained
theoretically for single sampling plans

Measuring Instruments/Apparatus/Software Required: MS Excel, Python

Data Generation Procedure:


In Excel, we generate 8 tables, each consisting of 20 samples. The number of defectives
in each sample follows a binomial distribution. We assume a lot size of 1000 for each
case, and a sample is accepted if the number of defectives in the sample is less than or
equal to 'c'. Otherwise, the sample is rejected.

1
Remove Watermark Wondershare
PDFelement

Describe Single Sampling Plan with an appropriate flowchart (to be drawn on your
own, not to be copied).
A Single Sampling Plan is a method used in quality control to inspect a specific number
of items from a production lot to determine whether the lot is acceptable or not.

….generated via Lucid

What is Rectifying Inspection? How does it affect average outgoing quality (AOQ)?
Rectifying inspection is a quality control process aimed at identifying and rectifying
defects in a batch of items to meet quality standards. Its impact on Average Outgoing
Quality (AOQ) varies:

o Positive Impact: It improves overall product quality, resulting in a higher AOQ


and minimizing defective product shipments.

o Resource-Intensive: It can be resource-intensive, increasing costs due to the labor


and time required for defect identification and correction.

o Reliability Concerns: The effectiveness of rectification is critical; incomplete


fixes may introduce uncertainty in AOQ.

o Customer Satisfaction: Ineffective rectification can harm customer satisfaction


and a brand's reputation.

2
Remove Watermark Wondershare
PDFelement

What is Average Total Inspection (ATI)?

Average Total Inspection (ATI) is a comprehensive quality control


method where each item in a production lot is individually inspected or
tested to provide a high level of confidence in the overall quality. It is
chosen in situations where exhaustive quality assurance is critical, even
if it involves significant time and resource investment.

Task I:
Collect and tabulate the data (as per the format provided) for the following values of the
sampling parameters. Generate 8 tables, with all the combinations of
𝑛1 , 𝑛2 , 𝑝1 , 𝑝2 and c=1,2

Lot size (N) : 1000 Number of samples to be drawn: 20 for each

Sample Size (n) : 𝑛1 , 𝑛2 Acceptance No (c) : 1, 2

Lot fraction defective (p): 𝑝1 , 𝑝2 from table

Table 1: 𝑁 = 1000 𝑛 = 11, 𝑝 = 0.02, 𝑐 = 1


Observation Number of Decision
Number Defectives Accept Reject
1 0 y
2 1 y
3 0 y
4 0 y
5 0 y
6 0 y
7 0 y
8 0 y
9 0 y
10 0 y
11 0 y
12 1 y
13 0 y
14 0 y
15 0 y
16 0 y
17 0 y
18 0 y
19 1 y
20 0 y
Probability of Acceptance, pa (experimental) = 1
Probability of Acceptance Pa (theoretical)= 0.980487368
AOQ= 0.019394
ATI= 30.298357

3
Remove Watermark Wondershare
PDFelement

Table 2: 𝑁 = 1000 𝑛 = 11, 𝑝 = 0.02, 𝑐=2


Observation Number of Decision
Number Defectives Accept Reject
1 0 y
2 1 y
3 0 y
4 1 y
5 0 y
6 0 y
7 0 y
8 0 y
9 0 y
10 1 y
11 0 y
12 0 y
13 0 y
14 0 y
15 0 y
16 0 y
17 0 y
18 0 y
19 1 y
20 0 y

Probability of Acceptance, pa (experimental) = 1


Probability of Acceptance Pa (theoretical)= 0.998829819
AOQ = 0.0197568
ATI= 12.15713

Table 3: 𝑁 = 1000 𝑛 = 11 , 𝑝 = 0.06, 𝑐=1


Observation Number of Decision
Number Defectives Accept Reject
1 2 y
2 2 y
3 0 y
4 1 y
5 0 y
6 1 y
7 0 y
8 0 y
9 2 y
10 1 y
11 1 y

4
Remove Watermark Wondershare
PDFelement

12 2 y
13 2 y
14 1 y
15 2 y
16 1 y
17 2 y
18 2 y
19 1 y
20 0 y

Probability of Acceptance, pa (experimental) = 0.6


Probability of Acceptance Pa (theoretical)= 0.861784183
AOQ= 0.0511382
ATI= 147.695624

Table 4: 𝑁 = 1000 𝑛 = 11 , 𝑝 = 0.06, 𝑐=2


Observation Number of Decision
Number Defectives Accept Reject
1 2 y
2 0 y
3 0 y
4 0 y
5 0 y
6 1 y
7 1 y
8 0 y
9 0 y
10 0 y
11 1 y
12 0 y
13 0 y
14 0 y
15 0 y
16 0 y
17 1 y
18 0 y
19 1 y
20 0 y

Probability of Acceptance, pa (experimental) = 1


Probability of Acceptance Pa (theoretical)= 0.975237153
AOQ= 0.05787056
ATI= 35.490607

5
Remove Watermark Wondershare
PDFelement

Table 5: 𝑁 = 1000 𝑛 = 38, 𝑝 = 0.02, 𝑐=1


Observation Number of Decision
Number Defectives Accept Reject
1 0 y
2 2 y
3 2 y
4 0 y
5 0 y
6 2 y
7 0 y
8 1 y
9 0 y
10 0 y
11 2 y
12 2 y
13 0 y
14 1 y
15 0 y
16 0 y
17 0 y
18 1 y
19 2 y
20 0 y

Probability of Acceptance, pa (experimental) = 0.7


Probability of Acceptance Pa (theoretical)= 0.823975026
AOQ=0.0158532
ATI= 207.33605

Table 6: 𝑁 = 1000 𝑛 = 38, 𝑝 = 0.02, 𝑐=2


Observation Number of Defectives Decision
Number Accept Reject
1 1 y
2 1 y
3 1 y
4 1 y
5 0 y
6 2 y
7 0 y
8 0 y
9 2 y
10 0 y
11 0 y
12 1 y
13 0 y

6
Remove Watermark Wondershare
PDFelement

14 1 y
15 1 y
16 2 y
17 0 y
18 0 y
19 0 y
20 2 y

Probability of Acceptance, pa (experimental) =1


Probability of Acceptance Pa (theoretical)= 0.959854558
AOQ= 0.0184676
ATI= 76.61949

Table 7: 𝑁 = 1000 𝑛 = 38, 𝑝 = 0.06, 𝑐=1


Observation Number of Defectives Decision
Number Accept Reject
1 3 y
2 1 y
3 3 y
4 1 y
5 2 y
6 4 y
7 3 y
8 2 y
9 1 y
10 2 y
11 4 y
12 3 y
13 2 y
14 4 y
15 2 y
16 1 y
17 3 y
18 3 y
19 4 y
20 3 y

Probability of Acceptance, pa (experimental) = 0.2


Probability of Acceptance Pa (theoretical)= 0.326276996
AOQ= 0.0188327
ATI=686.121526

7
Remove Watermark Wondershare
PDFelement

Table 8: 𝑁 = 1000 𝑛 = 38 , 𝑝 = 0.06, 𝑐 = 2


Observation Number of Decision
Number Defectives Accept Reject
1 3 y
2 1 y
3 2 y
4 1 y
5 2 y
6 4 y
7 3 y
8 2 y
9 0 y
10 2 y
11 4 y
12 3 y
13 0 y
14 4 y
15 2 y
16 1 y
17 2 y
18 3 y
19 4 y
20 3 y

Probability of Acceptance, pa (experimental) = 0.55


Probability of Acceptance Pa (theoretical)= 0.599087165
AOQ= 0.0345793
ATI=423.678306

For each of the above tables: calculate the following


The following formulae are used:

Number of times the lot is accepted


Probability of Acceptance, pa (experimental) =
Total number of samples drawn (20)
c
Probability of Acceptance Pa (theoretical) = 
i 0
n
C i p i (1  p ) n i

Pa p ( N  n)
AOQ = for a given p
N
𝐴𝑇𝐼 = 𝑛 + (1 − 𝑃𝑎 )(𝑁 − 𝑛)
The probability of acceptance, Pa as well as AOQ are to be computed for each set of n, c
and p.

8
Remove Watermark Wondershare
PDFelement

Task II: Construction of OC-Curve, AOQ Curve, ATI Curve

For 𝑁 = 1000, 𝑛 = 10, 25, 50 and 𝑐 = 0,1, 2, 3 prepare the OC curve and AOQ curve
as stated below.

i. OC-Curve for of Pa vs p for different c= 0,1,2,3; with n= 50

9
Remove Watermark Wondershare
PDFelement

ii.OC-Curve of Pa vs p for different n= 10, 25, 50; with c = 2

10
Remove Watermark Wondershare
PDFelement

11
Remove Watermark Wondershare
PDFelement

III.Curve for Average Outgoing Quality (AOQ) vs p for n=10, 25, 50 and c=2

12
Remove Watermark Wondershare
PDFelement

iv.Curve for Average Total Inspection (ATI) vs p for n=10, 50 and c=1, 3

13
Remove Watermark Wondershare
PDFelement

v. Results and Discussions:

a) Describe the effect of sample size and acceptance number on OC-Curve.

Sample Size (n):


 Increasing sample size improves defect detection, shifting the OC
curve left (lower acceptance probability).
 Decreasing sample size reduces defect detection, shifting the
OC curve right (higher acceptance probability).

Acceptance Number (c):


 Increasing acceptance number makes the process more lenient,
shifting the OC curve upward (higher acceptance probability).
 Decreasing acceptance number makes the process more stringent,
shifting the OC curve downward (lower acceptance probability).

b) Describe the effect of sample size and acceptance number on AOQ.

Sample Size (n):


 Increasing n generally improves AOQ by reducing the likelihood of shipping
defective products.
 Decreasing n tends to lower AOQ as it increases the risk of shipping defective
items.

Acceptance Number (c):


 Increasing c may reduce AOQ by allowing more non-conforming lots to be
accepted.
 Decreasing c can increase AOQ by rejecting more non-conforming lots but may
reduce the average quality of shipped products.

14
Remove Watermark Wondershare
PDFelement

vi. Conclusions:
In acceptance sampling simulation studies, such as single sampling, key conclusions arise
from the analysis of sample size (n) and acceptance number (c):
Sample Size (n):
i) Increasing n generally enhances quality control, resulting in better product quality for
customers and a lower risk of shipping defective lots.
ii) Decreasing n can compromise quality control, increasing the likelihood of shipping
defective lots.
Acceptance Number (c):
i) Increasing c makes the plan more lenient, improving the average quality of shipped
products but elevating the risk of non-conforming items.
ii) Decreasing c tightens the plan, improving quality control but potentially reducing the
average quality of shipped products.
iii) Choosing n and c involves a trade-off between quality control, resource use, and the
risk of shipping defects. Organizations should consider their quality needs, customer
satisfaction goals, and cost constraints when designing such plans. These findings
highlight the importance of balancing these factors to meet quality standards while
managing efficiency and customer expectations.

15
Remove Watermark Wondershare
PDFelement

You might also like