Complete Control Chart

Statistical Control Chart
Statistic technique that involves with

collecting sample of output process and
deciding whether the process can produce
product that have characteristic that fall
within predetermined (specification)
range.
Two type of cause
1. Common or random cause
in tolerance error, can not eliminated, variation from
worker, material, process (natural)
2. Assignable cause.
Significant error, out of tolerance error, must be and can
be solve immediately, unusual situation or process
defect.
Purpose of control chart: to detect assignable cause and

solve the cause immediately.
Variable and Attribute Control Chart
1. Variable Control Charts: to monitor characteristic that
can be measured and have a continuous scale, such as
height, gap, volume, width, etc.
a. Sample Control Chart (x-bar-chart and R-chart)
b. Individual Control Chart (x-chart and Moving
Range- Chart)
2. Attribute Control Chart: to monitor quality
characteristic that are counted (discrete) rather than
measure, such as yes-no or go-no-go decision.
a. Defect Control Chart (c-chart and u-chart)
b. Defectives Control Chart (p-chart and np-chart)
INDIVIDUAL CHART
FOR
VARIABLE CONTROL CHART
When to use
1. When we have variable data (continuous).
2. When data distribution is Normal Distribution.
3. When we can not use X-bar and R chart
because the measurement remain constant for
relatively long period .
ex: in batch operation where condition within
each batch remain constant.
Procedure
1. Collect at least 20 data points and arrange in
time order.
2. Determine if data is normal distribution: using
histogram and normality check.
3. Calculate the average X-bar and MR (Moving
Range)-bar.
4. Determine UCL and LCL of of X-bar and MR-
bar
5. Plot the points in to graph
STEP by STEP
STEP 1: Calculate X-bar
Number of values ( po int s ) k  ______________
Sum of the values   X  ______________
Average
__
X 
 X
 ________
k
STEP 2: Calculate MR-bar
Range ( R)  | X i 1  X i |  _________
Number of Moving Range  k 1  _________
Sum of the Moving range   MR  _________
Average moving range

____
 MR 
 MR
 _______
k 1
STEP by STEP cont’d
 STEP 3: Calculate Control Limits
_ _ ____
Estimate 3  3  2.66  MR  _______
___ _
Upper control lim it for X Chart  UCL X  X  3  ________
___ _
Lower control lim it for X cahrt  LCL X  X  3  ________
____
Upper control lim it for MR chart  UCL MR  3.267  MR  ____
Consideration
1. Individual chart does not detect process change as
quickly as X-bar and R chart, if it is possible using X-
bar and R chart, use them.
2. If the data come from non-normal distribution,
individual chart does not represent the process
accurately.
3. Range in individual chart and range in sample chart
are not the same. They are calculated and interpreted
differently. Range in individual does not separate
variation in the process.
Example
Example cont’d
X Chart LCLx UCLx
X Average X
12
10
0
1 2 3 4 5 6 7 8
Data Sequence
Example cont’d
Moving Range (R) Range (R)
UCL(MR)
7
0
1 2 3 4 5 6 7
Data Points
SAMPLE CHART FOR VARIABLE
CONTROL CHARTS
Control charts for variables monitor
characteristics that can be measured and
have a continuous scale, such as height,
weight, volume, or width. When an item is
inspected, the variable being monitored is
measured and recorded. For example, if we
were producing candles, height might be an
important variable. We could take samples of
candles and measure their heights.
Mean (x-Bar) Charts
A mean control chart is often referred to as an x-bar
chart. It is used to monitor changes in the mean of a
process. To construct a mean chart we first need to
construct the center line of the chart. To do this we take
multiple samples and compute their means. Usually
these samples are small, with about four or five
observations. Each sample has its own mean, ̅x. The
center line of the chart is then computed as the mean of
all n sample means, where n is the number of samples.
To construct the upper and lower control limits of the chart,we
use the following formulas:
Upper control limit (UCL)=
Lower control limit (LCL)=
Where :
=the Average of the sample means
Z= standard normal variable (2 for 95.44% confidence,
3 for 99.74%confidence)
=standard deviation of the distribution of sample
means,computed as 𝜎/
𝜎= population (process) standard deviation
n= sample size (number of observations per sample)
Example(1):
A quality control inspector at the Cocoa Fizz soft drink
company has taken twenty-five samples with four
observations each of the volume of bottles filled. The
data and the computed means are shown in the table.
If the standard deviation of the bottling operation is
0.14 ounces,use this information to develop control
limits of three standard deviations for the bottling
operation.
Solution:
The center line of the control data is the
average of the samples:
Control limits are :
UCL=16.16
LCL=15.74
The Resulting control chart is:
Range (R) Charts
Range (R) charts are another type of control chart for variables.
Whereas x-bar charts measure shift in the central tendency of the process, range
charts monitor the dispersion or variability of the process. The method for
developing and using R-charts is the same as that for x-bar charts. The center line of
the control chart is the average range, and the upper and lower control limits are
computed as follows:
where values for D4 and D3 are obtained from Table (1)

Example(2):
The quality control inspector at Cocoa Fizz would like to develop a range (R)
chart in order to monitor volume dispersion in the bottling process. Use the
data from Example (1) to develop control limits for the sample range.
Solution:
From the data in Example.1 you can see that the average sample range is:
From Table (1) for n=4
D4=2.28
The resulting control chart is:
Table(1) Factors for three-sigma control limits:
Using Mean and Range Charts Together:
both variables are important, it makes sense to
monitor a process using both mean and range
charts. It is possible to have a shift in the mean
of the product but not a change in the dispersion
a)there could be a shift in the dispersion of the
product without a change in the mean.
b) This condition would be detected by a range
chart but not by an x-bar chart. Because a shift in
either the mean or the range means that the
process is out of control, it is important to use
both charts to monitor the process.
Process shifts captured by x bar charts and R-charts:
ATTRIBUTE CONTROL CHART
Two kind of Attribute Chart
1. Defect Chart
2. Defectives Chart
Main different between two of them:

1. Defect means that the functionality of the product is still
working, but there is defect on the product.
ex: number of product has color defect in batch.
2. Defective means that functionality of the product is not working.
ex: number of apple rotten in batch.
3. p-chart is used when both total sample size and number of
defects can be computed.
4. C-chart is used when we can only compute the number of defect.
DEFECT CHART FOR
DEFECT CHART
1. c-Chart
2. u-Chart
C-Chart
C-chart is used to monitor the number of
defect per unit.
The center line of c-chart will be c-bar (the
average number of defect).
C-chart STEP
1. Collect data
2. Calculate c-bar as center line.
3. Calculate UCL and LCL:
4. Draw c-chart graph:

C-Chart Example
We want to monitor the number of weekly
customer complain in a hotel.
Data have been record for the last twenty

weeks
We want to develop c-chart using 3-sigma

control limit (z = 3).
C-Chart Example cont’d
Average number of complain: __

44
c
20
__
c  2. 2
Calculate control limit:
C-Chart Example cont’d
U chart
In this type of chart we plot the rate of
defectives i.e. the number of defectives
divided by the number of units inspected.
U chart is mathematically equivalent to the c-
chart.
u
c
u
 c
n n
•It can be shown that u obeys poisson
distribution with the following.
σ2 = u c u
n n
u u
UCL  u  3 LCL  u  3
n n
i.e. UCL = μ + 3σ LCL = μ - 3σ
EXAMPLE
Let the inspection unit be 100 sq m.
u
 c
= 22/8.4 = 2.62 defects per 100 sq m.
n
U Chart
DEFECTIVES CHART FOR
Defective
Consist of:
1. p-chart
2. np-chart
P-chart
- p-charts are used to measure the
proportion that is defective in sample.
- Center line is computed as the average
proportion defective (p-bar)
P-chart Step
1. Collect number of defective in samples.
2. Calculate defective proportion and the average

of defective proportion (p-bar):
__
Total number of defective
P
Total number of observation
3. Calculate UCL and LCL:
Where:
P-chart Example
Data of number of defective tires in 20 observations in
each sample (batch sample).
Number of sample = 20
Data given in the next slide!
Then construct 3-sigma control chart (z=3)

P-chart Example
P-chart Example
np-Chart
In this charts, we plot the number of defectives (per batch, per day, per
machine) as in the C charts.
However, the control limits in this chart are not based on the distribution
of rare events, but the rather on the binomial distribution. Therefore, this
chart should be used if the occurrence of defectives is not rare (e.g., they
occur in more than 5% of the units inspected).
There is a difference between a "P Chart" and an "Np Chart". A P chart is

one that shows the fraction defective (p), whereas the Np chart shows the
NUMBER of defectives (Np). They are practically the same thing with the
exception that an Np chart is used when the size of the subgroup (N) is
constant, and a P chart is used when it is NOT constant.
np-chart STEP
STEP 1: Collect the data
STEP 2: Record the number of defectives on a chart or spreadsheet,
along with the subgroup size. An example of a chart such as
this, is shown below:
Next slide!
np-chart STEP
np-chart STEP

STEP 3:

Record the number of defectives for each subgroup and record on the data sheet. Then total both
columns, from our example above you can see we had 272 defects, and 25 groups of 100 = 2500
total parts.
Use the following formula to determine your Pbar, (P) and to determine the percentage
defective:
NP = number of defectives = Np
Total Parts Inspected N
To indicate as a percentage, multiply your answer by 100.
From our chart, you can see that the formula is:
272 / (divided by) 2500 = 0.1088 and this answer is Pbar
Multiply this answer by 100 and you get 10.88%.

np-chart STEP

STEP 4:

Compute the Control Limits using the formula below:
Thus, with our example: 10.88 + 3 * square root of 10.88 * (1 - .1088)
10.88 + 3 * the square root of 10.88 (.89)
10.88 + 3 * 3.11 = 10.88 + 9.34 = 20.22
With our example: 10.88 - 3 * square root of 10.88 * (1 - .1088)
10.88 - 3 * 3.11 = 10.88 - 9.34 = 1.54

np-chart STEP
STEP 5: Draw the graph
END

Complete Control Chart

Uploaded by

Copyright:

Available Formats

Complete Control Chart

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Complete Control Chart

Uploaded by

Copyright:

Available Formats

What are the two types of causes in statistical process control?

What are the two types of causes in statistical process control?

What are the differences between variable and attribute control charts?

What are the differences between variable and attribute control charts?

Statistical Control Chart

Statistic technique that involves with

Purpose of control chart: to detect assignable cause and

Average moving range

Control limits are :

where values for D4 and D3 are obtained from Table (1)

From Table (1) for n=4

Main different between two of them:

4. Draw c-chart graph:

Data have been record for the last twenty

We want to develop c-chart using 3-sigma

Average number of complain: __

Let the inspection unit be 100 sq m.

2. Calculate defective proportion and the average

Data given in the next slide!

Then construct 3-sigma control chart (z=3)

There is a difference between a "P Chart" and an "Np Chart". A P chart is

To indicate as a percentage, multiply your answer by 100.

272 / (divided by) 2500 = 0.1088 and this answer is Pbar

Multiply this answer by 100 and you get 10.88%.

Thus, with our example: 10.88 + 3 * square root of 10.88 * (1 - .1088)

10.88 + 3 * the square root of 10.88 (.89)

10.88 + 3 * 3.11 = 10.88 + 9.34 = 20.22

With our example: 10.88 - 3 * square root of 10.88 * (1 - .1088)

10.88 - 3 * 3.11 = 10.88 - 9.34 = 1.54

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.