17 - Statistical Process Control 2

Download as pdf or txt
Download as pdf or txt
You are on page 1of 48

Total Quality

Management
Dr. Naga Vamsi Krishna Jasti
BITS Pilani Asst. Professor
Mechanical Engineering Department
Hyderabad Campus
BITS Pilani
Hyderabad Campus

Statistical Process Control


Scope
 Pareto Diagram
 Cause‐Effect Diagram
 Check Sheets
 Process Flow Diagram
 Scatter Diagram
 Histogram
 Control Charts
– Control charts for attributes
– Control charts for variables
3 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
Control Charts
 Focuses attention on detecting and monitoring
process variation over time
 Distinguishes special from common causes of
variation
 Serves as a tool for on‐going control
 Provides a common language for discussion process
performance
 Two types:
– Control charts for variables
– Control charts for attributes
4 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
Control Charts– contd.,
 Dr. Shewhart was the first to suggest the use.
 Three basic uses of control charts.
– First control shows the degree and nature of variation over
time. Can be used to determine whether a process is in a
state of statistical control or is out‐ of‐ control. It allows for
process improvement
– Second control charts are used to estimate the parameters
(mean, variation) of a process. By knowing the parameters
of a process, the output and the variability of the output
can be predicted.
– Third control charts are used to improve a process. Once a
process is in control, efforts to produce process variability
can begin. By reducing the variability of the process, the
overall quality of the final product increases.
5 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
How to Select a Control Chart

6 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


How to Select a Control Chart

DATA TYPE CHARTS MONITORS APPLICATIONS


Variable X‐Bar and S Process average and High volume, single
standard deviation characteristic
Sample size 8 or
larger
Variable X‐Bar and R Process average and High volume, single
range characteristic
Sample size
between 2 and 8
Variable X and MR Process average and Sensitivity not
moving range required
Sampling is costly
Long cycle time
(Note: Normality of
data must be
considered.)

7 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


How to Select a Control Chart
Attribute np Number of Pass/Fail Data
Defectives Constant Sample
Size
n > 3/p
Attribute p Proportion Pass/Fail Data
Defective Constant or
Variable Sample
Size
n > 3/p
Attribute c Number of Defects Multiple types of
defects on unit
Constant sample
size
n such that c > 7
Attribute u Number of Defects Multiple types of
per unit defects on unit
Constant or
variable sample
8 MM ZG522 ‐ Total Quality Management
size BITS Pilani, Hyderabad Campus
P Chart Vs u chart
 Use p charts when counting defective items & the sample size varies
 The p chart is one of four attribute control charts used to evaluate
the stability of a process over time using counted data. p charts are
sometimes confused with u charts.
– Defective Items ‐ p charts
• Each item is only counted once:

– car doors that need to be repainted


– bills that are wrong
– incomplete shipments
– Defects ‐ u charts
• Each item can have more than one defect:

– scratches on a car door


– errors on a bill
– missing products in a shipment

9 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
 The emphasis in using the control charts is on the
early detection and prevention of problems. By
preventing from occurring, productivity and profit
increases.
 Variable Control Charts:
 Used to monitor measurable quality characteristics of
a process. This may include temperature, viscosity,
weight, etc.,
 Main restriction is the a variables control chart can
monitor only one quality characteristic at a time.

10 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
 A variable charts monitors the mean value and the
variability of the quality characteristics being studied.
 Mean valued is monitored by X bar chart.
 Variability is measured via a range or moving range
(MR) chart or a standard deviation (S)
 The X bar chart with either R chart or an S chart
which measures within‐sample variability.
 R chart is used when the sample size is less than 8 and
S when it is greater than 8.

11 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control Chart Basic Procedure

 Choose the appropriate control chart for your data.


 Determine the appropriate time period for collecting and
plotting data.
 Collect data, construct your chart and analyze the data.
 Look for “out‐of‐control signals” on the control chart. When
one is identified, mark it on the chart and investigate the
cause. Document how you investigated, what you learned, the
cause and how it was corrected.
 Continue to plot data as they are generated. As each new data
point is plotted, check for new out‐of‐control signals.
 When you start a new control chart, the process may be out of
control. If so, the control limits calculated from the first 20
points are conditional limits. When you have at least 20
sequential points from a period when the process is operating
in control, recalculate control limits.
12 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
Control charts– contd.,

13 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,

14 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on R chart

15 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on R chart– contd.,

16 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on R chart– contd.,

17 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Appendix

18 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on S Chart

19 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on S Chart

20 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on S Chart– contd.,

21 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on S Chart– contd.,

22 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on MR (Moving
Range) Chart

23 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on MR (Moving
Range) Chart

24 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on MR (Moving
Range) Chart

25 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


An Example on MR (Moving
Range) Chart

26 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Interpreting Control Charts

27 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Rules
Rule1: A process is not in statistical control if any subgroup
statistic falls outside of the control limits. This point is marked as
‘X’ directly on the control chart.

28 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
Rule2: A process is not in statistical control if any two out of
three successive subgroup statistics fall in one of the A zones or
beyond on the same side of the centerline. The second of the
two pints in or beyond zone A is marked with ‘X’.

29 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
Rule3: A process is not in statistical control if any four out of five
successive subgroup statistics fall in one of the B zones or
beyond on the same side of the centerline. Only fourth is marked
with an ‘X’.

30 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
Rule3: A process is not in statistical control if any four out of five
successive subgroup statistics fall in one of the B zones or
beyond on the same side of the centerline. Only fourth is marked
with an ‘X’.

31 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts– contd.,
Rule4: A process is not in statistical control if any eight
successive points fall in one of the zone C on either side of the
centerline. Only eight point is marked with an ‘X’.

32 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Out-of-control signals

– A single point outside the control limits. In Figure 1, point


sixteen is above the UCL (upper control limit).
– Two out of three successive points are on the same side of
the centerline and farther than 2 σ from it. In Figure 1, point
4 sends that signal.
– Four out of five successive points are on the same side of
the centerline and farther than 1 σ from it. In Figure 1, point
11 sends that signal.
– A run of eight in a row are on the same side of the
centerline. Or 10 out of 11, 12 out of 14 or 16 out of 20. In
Figure 1, point 21 is eighth in a row above the centerline.
– Obvious consistent or persistent patterns that suggest
something unusual about your data and your process.

33 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Out-of-control signals

34 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Appendix

35 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Sample Size
 The characteristics of various sample sizes are summarized below.
Sample size of 2. The estimates of limits with n = 2 are likely to be
erratic and therefore it should not be used unless there is a good
engineering reason for it.
Sample size of 3. Though it can be used satisfactorily, but its use
makes calculations .‐ tedious as recurring decimals appear,
frequently.
Sample size of 4. It is the best sample size. It is stable and yet
sensitive.
Sample size of 5. It is also very satisfactory and best to use, as
calculations become very easy, particularly if measurements are in
decimals. However relatively more measurements have to be taken
to get a minimum number of samples.
Sample size of 6. It is generally not recommended unless
engineering or sub‐grouping reasons call for it. Two samples of 3 are
generally considered to be better than a sample of 6.

36 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Control charts for attributes
Control charts for attributes
 The quality characteristics can be justified or classified as
either conforming or non‐conforming based on whether or
not it has certain attributes.
 Attribute value can have only two values pass/fail,
conforming/non‐conforming, present/absent etc.,
 Special control charts for analyzing attributes data are
– p chart: plots the fraction non‐conforming per sample
– np chart: plots the number non‐conforming per sample
– c chart: plots the no of non‐conforming per inspection
unit
– u chart: plots the average no of non‐conforming per
inspection unit.
37 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
p Chart
 p Chart: p stands for proportion because it measures
the proportion of non‐conforming units in a group of
units being inspected.

38 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


p Chart

39 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


p Chart– Example

40 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


p Chart– Example

41 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


p Chart– Example

42 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


p Chart– Example
Based on the above results, the common modifications are:
1. Compute separate control limits for each sample based
on its specific sample size.
2. Compute the control limits based on an average sample
size.
3. Compute the control limits based on a standardized
fraction nonconforming.

43 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Problem 7
 Control Charts for X bar and R are to be established
on a certain dimension part, measured in millimeters.
Data were collected in subgroup sizes of 6 and are
given in next slide. Determine the trial central line and
control limits. Assume assignable causes and revise
the central line and limits.

44 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Problem 7
Subgroup X R
Subgrou X (bar) R Number (bar)
p 12 20.38 0.30
Number
13 20.40 0.33
1 20.35 0.34
14 20.41 0.36
2 20.40 0.36
15 20.45 0.34
3 20.36 0.32
16 20.34 0.37
4 20.65 0.36
17 20.36 0.37
5 20.20 0.36
18 20.42 0.73
6 20.40 0.35
19 20.50 0.38
7 20.43 0.31
20 20.31 0.35
8 20.37 0.34
21 20.39 0.38
9 20.48 0.30
22 20.39 0.33
10 20.42 0.37
23 20.40 0.32
11 20.39 0.29
24 20.41 0.34
25 20.40 0.30
45 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus
Solution 7
 From appendix (page number 630), for a subgroup of
6, obtain the values of A2, D3 and D4.
 A2= 0.483, D3 =0, D4= 2.004
 g= 25

46 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Solution 7

Based on the UCL, LCL, of x and R, eliminate all that fall above
and below the range and then recalculate the limits.

47 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus


Summary
 Pareto Diagram
 Cause‐Effect Diagram
 Check Sheets
 Process Flow Diagram
 Scatter Diagram
 Histogram
 Control Charts
– Control charts for attributes
– Control charts for variables
48 MM ZG522 ‐ Total Quality Management BITS Pilani, Hyderabad Campus

You might also like