Scribd
Upload
2K views4 pages

SPC Probs Solns s07

This document provides an example problem and solution demonstrating the use of statistical process control (SPC) charts to monitor a bottle filling process and a valve manufacturing process. For the bottle filling process, x-bar and R charts are constructed and analyzed to check if the process is in control with respect to the average volume of soda and range of volumes. For the valve process, a p chart is constructed and analyzed to check if the fraction of defective valves is within control limits.

Uploaded by

Siva Krishna Reddy Nallamilli
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2K views4 pages

SPC Probs Solns s07

This document provides an example problem and solution demonstrating the use of statistical process control (SPC) charts to monitor a bottle filling process and a valve manufacturing process. For the bottle filling process, x-bar and R charts are constructed and analyzed to check if the process is in control with respect to the average volume of soda and range of volumes. For the valve process, a p chart is constructed and analyzed to check if the fraction of defective valves is within control limits.

Uploaded by

Siva Krishna Reddy Nallamilli
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

63.

371

UMass Lowell
College of Management

T. Sloan

SPC Example Problems with Solutions


1. Super Fizz Cola Company wants to use SPC to monitor its bottle filling process. Every 20 minutes, they
took a random sample of four bottles from the production line and carefully measured the amount of cola
in each bottle. The results are reported in the table below.
Sample
1
2
3
4
5

351.2
350.3
351.4
350.8
350.6

Milliliters in each bottle


350.9
350.6
351.0
351.1
350.9
351.3
350.5
351.1
350.9
351.4

350.7
350.8
351.2
350.1
351.1

a. Is the volume of soda in a bottle a variable or an attribute?


b. What kind of control chart should be used to monitor the average volume of soda in each bottle?
Determine the three-sigma control limits for this chart.
c. Plot the average bottle volume for each sample on the appropriate chart. Is the process in-control
with respect to the average volume? What action should be taken?
d. What kind of control chart should be used to monitor the spread or dispersion of values? Determine
the three-sigma control limits for this chart.
e. Plot the volume range for each sample on the appropriate chart. Is the process in-control with respect
to the volume range? What action should be taken?
Solution:
First, compute the mean and range for each sample:
Sample
Average
Range

1
350.85
0.60

2
350.80
0.80

3
351.20
0.50

4
350.63
1.00

5
351.00
0.80

a. Volume is a continuous measure, so it is a variable.


b. An x-bar chart should be used to monitor the average volume. The process mean and standard
= 0.74. Now we
= 350.895 and R
deviation are unknown, so we use the numbers above to compute x
can compute the control limits:
UCL

= 350.895 + 0.729(0.74) = 351.4352 Ml.


+ A2 R
x

LCL

= 350.895 0.729(0.74) = 350.3548 Ml.


A2 R
x

The value for A2 is obtained from the table in the textbook (Table 6.1, p. 220) using n = 4.
c. The x-bar chart is shown below. All points are within the upper and lower control limits, so the
process is in-control with respect to the average volume. No action is necessary at this time.
d. An R chart should be used. The control limits are computed as:
UCLR

= 2.282(0.74) = 1.6872 Ml.


= D4 R

LCLR

= 0(0.74) = 0 Ml.
= D3 R

The values for D3 and D4 are obtained from the table in the textbook (Table 6.1, p. 220) using n = 4.
1

351.4

1.6

UCL

UCL

1.4
351.2

Volume Range (Ml.)

Average Volume (Ml.)

1.2

351.0

350.8

1.0

0.8

0.6

0.4

350.6

0.2
350.4

LCL

LCL

0.0
1

3
Sample

Figure 1: x-bar Chart for Super Fizz Problem

3
Sample

Figure 2: R Chart for Super Fizz Problem

e. The R chart is shown above. All of the values are within the upper and lower control limits, so the
process is in-control with respect to the range. No action is necessary at this time.

2. A company manufactures valves for industrial use. Ten samples of 15 valves each were taken from the
production line and tested. The results are reported below.
Number
Defective
3
1
0
0
0

Sample
1
2
3
4
5

Sample
6
7
8
9
10

Number
Defective
2
0
3
1
0

a. Compute the fraction defective for each sample.


b. Construct a p-chart for this process using control limits that include 95.5 percent of the sample means.
c. What comments can you make about the results? Is the process in-control? What action should be
taken?
Solution:
a. The fraction defective is computed by dividing the number defective by the number in each sample,
n = 15. The results are reported below.
Sample

10

0.200

0.067

0.000

0.000

0.000

0.133

0.000

0.200

0.067

0.000

b. q
First, we compute
the average proportion defective: p = 0.0667. The standard deviation is: p =
q
p(1

p)

0.0667(10.0667)
=
= 0.0644. To account for 95.5 percent of the random variation in the
n
15
process, we set z = 2 (two standard deviations). So the control limits are:
UCLp

p + zp = 0.0667 + 2(0.0644) = 0.19548

LCLp

p zp = 0.0667 2(0.0644) = 0.06215 0.

Note that we had to round the LCL value to zero it is impossible to have a negative control limit.
c. The control chart is shown below. Samples 1 and 8 are above the upper control limits. We should
investigate possible causes of these out-of-control values.

UCL

0.20

Fraction Defective

0.15

0.10

0.05

0.00
LCL
1

Sample

Figure 3: p Chart for Valve Problem

10

SPC Formulas
For x
Charts

(unknown process mean and standard deviation)

A2 R
LCLx = x

+ A2 R
UCLx = x

Centerline : x

For R Charts

LCLR = D3 R

UCLR = D4 R

Centerline : R
For p Charts
Centerline : p
p =

UCLp = p + zp

LCLp = p zp

p(1 p)
n

Factors for Computing Three-Sigma Control Chart Limits


Sample
Size n

A2

D3

D4

2
3
4
5
6
7
8
9
10
12

1.880
1.023
.729
.577
.483
.419
.373
.337
.308
.266

0
0
0
0
0
.076
.136
.184
.223
.284

3.267
2.575
2.282
2.115
2.004
1.924
1.864
1.816
1.777
1.716

(Same as Table 6.1 on page 220 of textbook)

You might also like