SPC For Operators

5/02/2014
Statistical Process
Control
Operators Session
Quality Improvement and Statistics
• Definitions of Quality
Quality means fitness for use

- quality of design
- quality of conformance
Quality is inversely proportional to
variability.
• Quality Improvement
Quality improvement is the reduction of
variability in processes and products.
Alternatively, quality improvement is also

seen as “waste reduction”.
Powered by HERA CONSULTING 1

5/02/2014
• Statistical process control is a

collection of tools that when used
together can result in process stability
and variance reduction.
Statistical Process Control

The seven major tools are
1) Histogram
2) Pareto Chart
4) Cause and Effect Diagram
5) Defect Concentration Diagram
6) Control Chart
7) Scatter Diagram
8) Check Sheet
Chapter 1:
SPC
capability machines
X-R card

5/02/2014
What is meant by
Statistical Process Control?
Statistical Process Control (S.P.C.)
• This is a control system which uses

statistical techniques for knowing, all the
time, changes in the process.
• It is an effective method in preventing

defects and helps continuous quality
improvement.
What does S.P.C. mean?
• Statistical:
• Statistics are tools used to make
predictions on performance.
• There are a number of simple methods
for analysing data and, if applied
correctly, can lead to predictions with a
high degree of accuracy.

5/02/2014

• Process:
• The process involves people, machines,
materials, methods, management and
environment working together to
produce an output, such as an end
product.

• Control:
• Controlling a process is guiding it and
comparing actual performance against
a target.
• Then identifying when and what
corrective action is necessary to
achieve the target.
S.P.C.
• Statistics aid in making decisions about
a process based on sample data and
the results predict the process as a
whole.

5/02/2014
The Process
Man Machines Material
Output
Management Methods Mother Nature
Definition
• S.P.C. is statistical analysis of

the predictability and
capacity of a process to give
a uniform product.
The Aim of S.P.C. - Detection Strategy
• Detection:
This focuses on identification of
problems after production, by 100%
inspection or by customer complaints.
• It is a historically-based strategy.

5/02/2014
The Aim of S.P.C. - Detection Strategy
Detection Drawbacks:
• Production is already made.
• Customer dissatisfaction.
• Inflated costs - rework; inspection.
• Repetitive problems.
• Neglected improvements.
The Aim of S.P.C. - Prevention Strategy
• Prevention:
This focuses on in-process production
and identification of problems through
analysis of process capability.
• It is a future-orientated strategy.
The Aim of S.P.C. - Prevention Strategy
Prevention Benefits:
• Improved design and process
capability.
• Improved manufacturing quality.
• Improved organisation.
• Continuous Improvement.

5/02/2014
S.P.C. as a Prevention
Tool
• The S.P.C. has to be looked at as a
stage towards completely preventing
defects.
• With stable processes, the cost of
inspection and defects are significantly
reduced.
The Benefits of S.P.C.
• Assesses the design intent.

• Achieves a lower cost by providing an
early warning system.
• Monitors performance, preventing
defects.
• Provides a common language for
discussing process performance.
Process Variations
Process Element Variable Examples

Machine………………………….Speed, operating
temperature, feed rate
Tools………………………………..Shape, wear rate
Fixtures…………………………..Dimensional accuracy
Materials…………………………Composition, dimensions
Operator…………………………Choice of set-up, fatigue
Maintenance…………………Lubrication, calibration
Environment…………………Humidity, temperature

5/02/2014
Process Variations
• No industrial process or machine is able to
produce consecutive items which are identical
in appearance, length, weight, thickness etc.
• The differences may be large or very small,
but they are always there.
• The differences are known as ‘variation’.
This is the reason why ‘tolerances’ are used.
Stability
• Common causes are the many sources of
variation that are always present.
• A process operates within ‘normal variation’
when each element varies in a random
manner, within expected limits, such that the
variation cannot be blamed on one element.
• When a process is operating with common
causes of variation it is said to be stable.
Process Control
• The process can only be termed

‘under control’ if it gives
predictable results.
• Its variability is stable over a long

period of time.

5/02/2014
Process Control Charts

• Graphs and charts have to be chosen
for their simplicity, usefulness and
visibility.
• They are simple and effective tools
based on process stability monitoring.
• They give evidence of whether a
process is operating in a state of
control and signal the presence of any
variation.
Data Interpretation
Consider these 50 measurements
Bore Diameter 36.32 ±0.05mm (36.27 - 36.37mm)
1 36.36 11 36.37 21 36.34 31 36.35 41 36.36

2 36.34 12 36.35 22 36.37 32 36.35 42 36.37
3 36.34 13 36.32 23 36.34 33 36.36 43 36.37
4 36.33 14 36.35 24 36.35 34 36.37 44 36.35
5 36.35 15 36.34 25 36.34 35 36.34 45 36.37
6 36.33 16 36.34 26 36.35 36 36.36 46 36.36
7 36.33 17 36.35 27 36.36 37 36.38 47 36.35
8 36.34 18 36.33 28 36.33 38 36.34 48 36.34
9 36.35 19 36.32 29 36.36 39 36.35 49 36.35
10 36.35 20 36.35 30 36.38 40 36.35 50 36.34
Data Interpretation
• As a set of numbers it is difficult to see
any pattern.
• Within the table, numbers 30 and 37
were outside the tolerance – but were
they easy to spot?
• A way of obtaining a pattern is to group
the measurements according to size.

5/02/2014
Data Interpretation – Tally Chart

36.39
36.38 • The tally chart

36.37 groups the
36.36
measurements
36.35
36.34
together by size
36.33 as shown.
36.32
• The two parts that
36.31
36.30
were out of
36.29 tolerance are now
36.28
easier to detect
(36.38mm).
Tally Chart - Frequency

36.39
2
36.38
6
• The tally chart shows
36.37
7 patterns and we can
36.36
16 obtain the RANGE -
36.35
12 36.32mm to
36.34
36.33
5 36.38mm.
2
36.32 • The most
36.31
FREQUENTLY
36.30
OCCURRING size is
36.29
36.28
36.35mm.
Tally Chart - Information
• The tally chart gives us further information:

• The number of bores at each size;
• The number of bores at the most common
size;
• The number of bores above and below the
most common size (36.35mm) -
• number above 36.35mm is 7+6+2=15
• number below 36.35mm is 12+5+2=19

5/02/2014
Histogram
We can redraw the frequency chart as a bar chart
known as a histogram:
16
14
12
10
0 36.31 36.32 36.33 36.34 36.35 36.36 36.37 36.38 36.39
Smoothed Frequency
If we now draw a smooth curve through the top of each box
we get a bell-shaped pattern:
16
14
12
10
0 36.31 36.32 36.33 36.34 36.35 36.36 36.37 36.38 36.39
Distribution
• The bell-shaped pattern is fairly typical of

most industrial processes.
• There is a central value at the highest point of
the curve and the pattern of results spread
out equally on both sides of the central value.
• The further we move from the central value,
the fewer values we will find.
• This bell-shaped pattern is known as the
‘NORMAL DISTRIBUTION’.

5/02/2014
Population and Sampling Distributions

Three population Distribution of
distributions sample means
Mean of sample means = x
Beta
Standard
deviation of σ
Normal the sample = σx = n
means
Uniform
| | | | | | |
-3σx -2σx -1σx x +1σx +2σx +3σx

95.45% fall within ± 2σx
99.73% of all x
fall within ± 3σx Figure S6.3
Sampling Distribution
Sampling
distribution
of means
Process
distribution
of means
x=µ
(mean)
Figure S6.4
Normal Distribution
• The bell-shaped pattern known as ‘Normal
Distribution’ is one that we would expect to
see where the process is running in a
stable condition.
• Where you work in a manufacturing
environment, why not perform the exercise
on 50 parts for yourself and see if your
process is in a stable condition!

5/02/2014
Basic Principles
• A process that is operating with only

chance causes of variation present is said
to be in statistical control.
• A process that is operating in the presence
of assignable causes is said to be out of
control.
• The eventual goal of SPC is the elimination
of variability in the process.
Basic Principles
Basic Principles
A typical control chart has control limits set at values
such that if the process is in control, nearly all points
will lie within the upper control limit (UCL) and the
lower control limit (LCL).

5/02/2014
Basic Principles
Basic Principles
Important uses of the control chart
1. Most processes do not operate in a state of statistical
control
2. Consequently, the routine and attentive use of control
charts will identify assignable causes. If these causes
can be eliminated from the process, variability will be
reduced and the process will be improved
3. The control chart only detects assignable causes.
Management, operator, and engineering action will be
necessary to eliminate the assignable causes.
Samples
To measure the process, we take
samples and analyze the sample
statistics following these steps
Each of these
(a) Samples of the represents one
product, say five sample of five
boxes of cereal boxes of cereal
taken off the filling
# #
machine line, vary
Frequency
# # #
from each other in
# # # #
weight
# # # # # # #
# # # # # # # # # #
Weight

5/02/2014
Samples
The solid line
represents the
(b) After enough distribution
samples are
taken from a
stable process,
Frequency
they form a
pattern called a
distribution
Weight
Samples
(c) There are many types of distributions, including
the normal (bell-shaped) distribution, but
distributions do differ in terms of central
tendency (mean), standard deviation or
variance, and shape
Figure S6.1
Frequency
Central tendency Variation Shape
Weight Weight Weight
Samples
(d) If only natural
causes of
variation are
Frequency
present, the Prediction

output of a
process forms a
distribution that
is stable over Weight
time and is
predictable Figure S6.1

5/02/2014
Samples
?
?? ??
? ?
(e) If assignable ?
?
? ?
?
?
causes are ??
? ??
?
present, the
Frequency
Prediction
process output is
not stable over
time and is not
predicable
Weight
Figure S6.1
Control Charts
Constructed from historical data,
the purpose of control charts is to
help distinguish between natural
variations and variations due to
assignable causes
Process Control
(a) In statistical
control and
capable of
Frequency producing within
control limits
Lower control limit Upper control limit
(b) In statistical
control but not
capable of
producing within
control limits
(c) Out of control
Size
(weight, length, speed, etc.) Figure S6.2

5/02/2014
Types of Data
Variables Attributes
Characteristics that Defect-related
can take any real characteristics
value Classify products
May be in whole or as either good or
in fractional bad or count
numbers defects
Continuous random Categorical or
variables discrete random
variables
Control Charts for Variables
For variables that have

continuous dimensions
Weight, speed, length,
strength, etc.
x-charts are to control
the central tendency of the process
R-charts are to control the dispersion of
the process
These two charts must be used together
Basic Principles
Types the control chart
• Variables Control Charts
– These charts are applied to data that follow a
continuous distribution.
• Attributes Control Charts
– These charts are applied to data that follow a
discrete distribution.

5/02/2014
Basic Principles
Popularity of control charts
1) Control charts are a proven technique for improving

productivity.
2) Control charts are effective in defect prevention.
3) Control charts prevent unnecessary process adjustment.
4) Control charts provide diagnostic information.
5) Control charts provide information about process
capability.
Design of a Control Chart

Suppose we have a process that we assume the
true process mean is µ = 74 and the process
standard deviation is σ = 0.01. Samples of size 5
are taken giving a standard deviation of the sample
average, is
σ 0.01
σx = = = 0.0045
n 5

• Control limits can be set at 3 standard
deviations from the mean in both directions.
• “3-Sigma Control Limits”
UCL = 74 + 3(0.0045) = 74.0135
CL= 74
LCL = 74 - 3(0.0045) = 73.9865

5/02/2014
Introduction to Control Charts

2 Design of a Control Chart
• Choosing the control limits is equivalent to

setting up the critical region for hypothesis
testing
H0: µ = 74
H1: µ ≠ 74
Introduction to Control Charts

Basic Principles

5/02/2014
Rational Subgroups
• Subgroups or samples should be selected

so that if assignable causes are present, the
chance for differences between subgroups
will be maximized, while the chance for
differences due to these assignable causes
within a subgroup will be minimized.
Rational Subgroups
Constructing Rational Subgroups
• Select consecutive units of production.
– Provides a “snapshot” of the process.
– Good at detecting process shifts.
• Select a random sample over the entire sampling
interval.
– Good at detecting if a mean has shifted
– out-of-control and then back in-control.
Analysis of Patterns on Control Charts

• Look for “runs” - this is a sequence of
observations of the same type (all above the
center line, or all below the center line)
• Runs of say 8 observations or more could
indicate an out-of-control situation.
– Run up: a series of observations are increasing
– Run down: a series of observations are decreasing

5/02/2014

5/02/2014
X-bar and R Control Charts

5/02/2014

5/02/2014
Computer Construction

5/02/2014
Control Charts for Individual Measurements

• What if you could not get a sample size greater than 1 (n
=1)? Examples include
– Automated inspection and measurement technology is
used, and every unit manufactured is analyzed.
– The production rate is very slow, and it is inconvenient
to allow samples sizes of N > 1 to accumulate before
analysis
– Repeat measurements on the process differ only
because of laboratory or analysis error, as in many
chemical processes.
• The individual control charts are useful for samples of
sizes n = 1.
• The moving range (MR) is defined as the

absolute difference between two successive
observations:
MRi = |xi - xi-1|
which will indicate possible shifts or
changes in the process from one observation
to the next.

5/02/2014
Interpretation of the Charts

• X Charts can be interpreted similar to x charts. MR charts
cannot be interpreted the same as x or R charts.
• Since the MR chart plots data that are “correlated” with
one another, then looking for patterns on the chart does not
make sense.
• MR chart cannot really supply useful information about
process variability.
• More emphasis should be placed on interpretation of the X
chart.
P Chart (Control Chart for Proportions)

and nP Chart

5/02/2014

and nP Chart

and nP Chart

and nP Chart

5/02/2014
U Chart (Control Chart for Average

Number of Defects per Unit) and C
Chart

Chart

Chart

5/02/2014

Chart
Control Chart Performance

Average Run Length
• The average run length (ARL) is a very
important way of determining the appropriate
sample size and sampling frequency.
• Let p = probability that any point exceeds the
control limits. Then,

5/02/2014
Setting Chart Limits

For x-Charts when we know σ
Upper control limit (UCL) = x + zσx
Lower control limit (LCL) = x - zσx
where x = mean of the sample means or a target
value set for the process
z = number of normal standard deviations
σx = standard deviation of the sample means
= σ/ n
σ = population standard deviation
n = sample size
Control Charts for Variables
For variables that have

continuous dimensions
Weight, speed, length,
strength, etc.
x-charts are to control
the central tendency of the process
R-charts are to control the dispersion of
the process
These two charts must be used together

5/02/2014
Setting Control Limits

Hour 1 Hour Mean Hour Mean
Sample Weight of 1 16.1 7 15.2
Number Oat Flakes 2 16.8 8 16.4
1 17 3 15.5 9 16.3
2 13 4 16.5 10 14.8
3 16 5 16.5 11 14.2
4 18 6 16.4 12 17.3
n=9 5 17
6 16 For 99.73% control limits, z = 3
7 15
8 17 UCLx = x + zσx = 16 + 3(1/3) = 17 ozs
9 16
Mean 16.1 LCLx = x - zσx = 16 - 3(1/3) = 15 ozs
σ= 1

Control Chart
for sample of Variation
Out of due to
9 boxes control assignable
causes
17 = UCL
Variation due
16 = Mean to natural
causes
15 = LCL
| | | | | | | | | | | |
Variation
due to
1 2 3 4 5 6 7 8 9 10 11 12 Out of assignable
Sample number control causes

For x-Charts when we don’t know σ
Upper control limit (UCL) = x + A2R

Lower control limit (LCL) = x - A2R
where R = average range of the samples

A2 = control chart factor found in Table S6.1
x = mean of the sample means

5/02/2014
Control Chart Factors

Sample Size Mean Factor Upper Range Lower Range
n A2 D4 D3
2 1.880 3.268 0
3 1.023 2.574 0
4 .729 2.282 0
5 .577 2.115 0
6 .483 2.004 0
7 .419 1.924 0.076
8 .373 1.864 0.136
9 .337 1.816 0.184
10 .308 1.777 0.223
12 .266 1.716 0.284
Process average x = 12 gr
Average range R = .25
Sample size n = 5

Sample size n = 5
UCLx = x + A2R
= 12 + (.577)(.25)
= 12 + .144
= 12.144 kg
From Table

5/02/2014

Sample size n = 5
UCLx = x + A2R UCL = 12.144

= 12 + (.577)(.25)
= 12 + .144 Mean = 12
= 12.144 gr
LCLx = x - A2R LCL = 11.857

= 12 - .144
= 11.857 gr
Restaurant Control Limits

For salmon filets at Darden Restaurants
x Bar Chart
Sample Mean
11.5 – UCL = 11.524
11.0 – x – 10.959
10.5 – LCL – 10.394

| | | | | | | | |
1 3 5 7 9 11 13 15 17
Range Chart
0.8 –
Sample Range
UCL = 0.6943
0.4 –
R = 0.2125
0.0 –| | | | | | | | | LCL = 0
1 3 5 7 9 11 13 15 17
Restaurant Control Limits

Capability Histogram
LSL USL
Specifications
LSL 10
USL 12
Capability
Mean = 10.959
Std.dev = 1.88
Cp = 1.77
Cpk = 1.7

5/02/2014
R – Chart
Type of variables control chart
Shows sample ranges over time
Difference between smallest and
largest values in sample
Monitors process variability
Independent from process mean

For R-Charts
Upper control limit (UCLR) = D4R

Lower control limit (LCLR) = D3R
where
R = average range of the samples
D3 and D4 = control chart factors from Table S6.1

Average range R = 5.3 cm
Sample size n = 5
From Table S6.1 D4 = 2.115, D3 = 0
UCLR = D4R UCL = 11.2

= (2.115)(5.3)
= 11.2 cm Mean = 5.3
LCLR = D3R LCL = 0

= (0)(5.3)
= 0 cm

5/02/2014
Mean and Range Charts

(a)
These (Sampling mean is
sampling shifting upward
distribution but range is
s result in consistent)
the charts
below
UCL
(x-chart
x-chart detects shift in
central
LCL tendency)
UCL
(R-chart does
R-chart not detect
change in mean)
LCL
Mean and Range Charts

(b)
These
sampling (Sampling
distribution mean is
s result in constant but
dispersion is
the charts
below increasing)
UCL
(x-chart does not
x-chart detect the
increase in
LCL dispersion)
UCL
(R-chart detects
R-chart increase in
dispersion)
LCL
Steps In Creating Control Charts
1. Take samples from the population and

compute the appropriate sample statistic
2. Use the sample statistic to calculate control
limits and draw the control chart
3. Plot sample results on the control chart and
determine the state of the process (in or out of
control)
4. Investigate possible assignable causes and
take any indicated actions
5. Continue sampling from the process and reset
the control limits when necessary

5/02/2014
Manual and Automated Control Charts
Control Charts for Attributes

For variables that are categorical
Good/bad, yes/no,
acceptable/unacceptable
Measurement is typically counting
defectives
Charts may measure
Percent defective (p-chart)
Number of defects (c-chart)
Control Limits for p-Charts

Population will be a binomial
distribution, but applying the Central
Limit Theorem allows us to assume a
normal distribution for the sample
statistics
UCLp = p + zσp^ σ^ =
p(1 - p)
p n
LCLp = p - zσp^
where p = mean fraction defective in the sample
z = number of standard deviations
σp^ = standard deviation of the sampling distribution
n = sample size

5/02/2014
p-Chart for Data Entry

Sample Number Fraction Sample Number Fraction
Number of Errors Defective Number of Errors Defective
1 6 .06 11 6 .06
2 5 .05 12 1 .01
3 0 .00 13 8 .08
4 1 .01 14 7 .07
5 4 .04 15 5 .05
6 2 .02 16 4 .04
7 5 .05 17 11 .11
8 3 .03 18 3 .03
9 3 .03 19 0 .00
10 2 .02 20 4 .04
Total = 80
80 (.04)(1 - .04)
p= =.04
(100)(20) σp^ = = .02
100

UCLp = p + zσ^p = .04 + 3(.02) = .10
LCLp = p - zσ^p = .04 - 3(.02) = 0
.11 –
.10 – UCLp = 0.10
Fraction defective
.09 –
.08 –
.07 –
.06 –
.05 –
.04 – p = 0.04
.03 –
.02 –
.01 – LCLp = 0.00
| | | | | | | | | |
.00 –
2 4 6 8 10 12 14 16 18 20
Sample number

UCLp = p + zσ^p = .04 + 3(.02) = .10
LCLp = p - zσ^p = .04 - 3(.02) = 0
.11 –
.10 – UCLp = 0.10
Fraction defective
.09 –
Possible assignable
.08 –
causes present
.07 –
.06 –
.05 –
.04 – p = 0.04
.03 –
.02 –
.01 – LCLp = 0.00
| | | | | | | | | |
.00 –
2 4 6 8 10 12 14 16 18 20
Sample number

5/02/2014
Control Limits for c-Charts

Population will be a Poisson distribution,
but applying the Central Limit Theorem
allows us to assume a normal
distribution for the sample statistics
UCLc = c + 3 c LCLc = c - 3 c
where c = mean number defective in the sample
c-Chart for Cab Company
c = 54 complaints/9 days = 6 complaints/day
UCLc = c + 3 c 14 – UCLc = 13.35

Number defective
=6+3 6 12 –
= 13.35 10 –
8 –
6 – c= 6
LCLc = c - 3 c 4 –
=6-3 6 2 – LCLc = 0
0 – | | | | | | | | |
=0 1 2 3 4 5 6 7 8 9
Day
Managerial Issues and

Control Charts
Three major management decisions:
Select points in the processes that

need SPC
Determine the appropriate charting
technique
Set clear policies and procedures

5/02/2014
Which Control Chart to Use

Variables Data
Using an x-Chart and R-Chart
1. Observations are variables

2. Collect 20 - 25 samples of n = 4, or n = 5, or
more, each from a stable process and compute
the mean for the x-chart and range for the R-
chart
3. Track samples of n observations each.
Table S6.3

Attribute Data
Using the p-Chart
1. Observations are attributes that can be

categorized as good or bad (or pass–fail, or
functional–broken), that is, in two states.
2. We deal with fraction, proportion, or percent
defectives.
3. There are several samples, with many
observations in each. For example, 20 samples
of n = 100 observations in each.
Table S6.3

Attribute Data
Using a c-Chart
1. Observations are attributes whose defects per

unit of output can be counted.
2. We deal with the number counted, which is a
small part of the possible occurrences.
3. Defects may be: number of blemishes on a
desk; complaints in a day; crimes in a year;
broken seats in a stadium; typos in a chapter of
this text; or flaws in a bolt of cloth.

5/02/2014
Patterns in Control Charts

Upper control limit
Target
Lower control limit

Normal behavior. Process is
“in control.”

Upper control limit
Target
Lower control limit

One plot out above (or
below). Investigate for
cause. Process is “out of
control.”

Upper control limit
Target
Lower control limit

Trends in either direction, 5
plots. Investigate for cause
of progressive change.

5/02/2014

Upper control limit
Target
Lower control limit

Two plots very near lower (or
upper) control. Investigate
for cause.

Upper control limit
Target
Lower control limit

Run of 5 above (or below)
central line. Investigate for
cause.

Upper control limit
Target
Lower control limit

Erratic behavior. Investigate.

5/02/2014
C- Chart
Process Capability
The natural variation of a process
should be small enough to produce
products that meet the standards
required
A process in statistical control does not
necessarily meet the design
specifications
Process capability is a measure of the
relationship between the natural
variation of the process and the design
specifications
• A process is operating with only chance causes of variation present is said to

be in statistical control.
• A process that is operating in the presence of assignable causes is said to be
out of control.

5/02/2014
Process Capability
• Process capability refers to the performance of

the process when it is operating in control.
• Two graphical tools are helpful in assessing
process capability:
• Tolerance chart (or tier chart)
• Histogram
Process Capability
Process Capability

5/02/2014
Process Capability
Process Capability
Process Capability

5/02/2014
Process Capability Ratio
Upper Specification - Lower Specification

Cp =
6σ
A capable process must have a Cp of at

least 1.0
Does not look at how well the process
is centered in the specification range
Often a target value of Cp = 1.33 is used
to allow for off-center processes
Six Sigma quality requires a Cp = 2.0

Insurance claims process
Process mean x = 210.0 minutes
Process standard deviation σ = .516 minutes
Design specification = 210 ± 3 minutes

Cp = 6σ


Cp =
6σ
213 - 207
= = 1.938
6(.516)

5/02/2014


Cp = 6σ
213 - 207
=
6(.516)
= 1.938 Process is
capable
Process Capability Index

Upper Lower
Cpk = minimum of Specification
, -x x - Specification
Limit Limit
3σ 3σ
A capable process must have a Cpk of at

least 1.0
A capable process is not necessarily in the
center of the specification, but it falls within
the specification limit at both extremes
New Cutting Machine

New process mean x = .250 cm
Process standard deviation σ = .0005 cm
Upper Specification Limit = .251 cm
Lower Specification Limit = .249 cm

5/02/2014

New Cutting Machine
(.251) - .250
Cpk = minimum of ,
(3).0005

New Cutting Machine
(.251) - .250 .250 - (.249)

Cpk = minimum of ,
(3).0005 (3).0005
Both calculations result in

New machine is
.001
Cpk =
.0015
= 0.67 NOT capable
Process Capability
• Cp represents the precision, but not the accuracy of the process in
respect to the tolerance window.
High Accuracy but low High Precision but low

precision Accuracy

5/02/2014
Cpk Graph (Minitab)

Process Capability of CONTROL
LSL USL
Process Data W ithin
LSL 65 Overall
T arget *
USL 85 Potential (W ithin) Capabilit y
Sample Mean 71.7151 Cp 0.91
Sample N 73 CPL 0.61
StDev(W ithin) 3.67538 CPU 1.20
StDev(Overall) 6.4853 Cpk 0.61
Overall Capability
Pp 0.51
PPL 0.35
PPU 0.68
Ppk 0.35
Cpm *
54 60 66 72 78 84
Observed Performance Exp. W ithin Performance Exp. Overall Performance
PPM < LSL 123287.67 PPM < LSL 33846.99 PPM < LSL 150234.16
PPM > USL 0.00 PPM > USL 150.42 PPM > USL 20257.02
PPM Tot al 123287.67 PPM T otal 33997.41 PPM Total 170491.18
Control Chart Selection

Quality Characteristic
variable attribute
defective defect
no
n>1? x and MR
yes constant
yes constant
p or sampling
sample
np unit?
n>=10 or no size?
x and R
computer? yes no
no
yes
p-chart with c u
x and s variable sample
size
143
Control Chart Design Issues

• Basis for sampling
• Sample size
• Frequency of sampling
• Location of control limits
144

5/02/2014
Pre-Control
LTL UTL
Red Red
Zone Green Zone Zone
nominal
value
Yellow Zones
146
Interpreting Cpk
Cpk = negative number
Cpk = zero
Cpk = between 0 and 1
Cpk = 1
Cpk > 1
Figure S6.8

5/02/2014

Average Run Length
• The average run length (ARL) is a very
important way of determining the appropriate
sample size and sampling frequency.
• Let p = probability that any point exceeds the
control limits. Then,

5/02/2014
Acceptance Sampling
Form of quality testing used for

incoming materials or finished goods
Take samples at random from a lot
(shipment) of items
Inspect each of the items in the sample
Decide whether to reject the whole lot
based on the inspection results
Only screens lots; does not drive
quality improvement efforts
Acceptance Sampling
Form of quality testing used for
incoming materials or finished
goods
Take samples at random from a
lot (shipment) of items
Inspect each of the items in the
sample Rejected lots can
be:
Decide whether to reject the
whole lot based on the inspection Returned to the
supplier
results
Culled for
Only screens lots; does not defectives
(100% inspection)
drive quality improvement
efforts
Operating Characteristic Curve
Shows how well a sampling plan

discriminates between good and
bad lots (shipments)
Shows the relationship between
the probability of accepting a lot
and its quality level

5/02/2014
The “Perfect” OC Curve

Keep
whole
shipment
100 –
75 –
Return
P(Accept Whole
whole
50 –
shipment
Shipment)
Cut-Off
25 –
0 |– | | | | | | | | | |
0 10 20 30 40 50 60 70 80 90 100
% Defective in Lot
An OC Curve Figure S6.9

100 –
95 – α = 0.05 producer’s risk for AQL
75 –
Probability
of 50 –
Acceptance
25 –
10 –
β = 0.10 Percent
0 |– | | | | | | | |
0 1 2 3 4 5 6 7 8 defective
AQL LTPD
Consumer’s
Good Indifference
risk for LTPD Bad lots
lots zone
AQL and LTPD
Acceptable Quality Level (AQL)

Poorest level of quality we are
willing to accept
Lot Tolerance Percent Defective
(LTPD)
Quality level we consider bad
Consumer (buyer) does not want to
accept lots with more defects than
LTPD

5/02/2014
Control Chart Decision Tree

Control Charts
X bar , R
X bar, S
IX, Moving Range

Start
p (fraction defective) or
np (number def. Per
sample
p
c (defects per sample

or
u defects per unit
u
Producer’s and Consumer’s Risks

Producer's risk (α)
Probability of rejecting a good lot
Probability of rejecting a lot when the
fraction defective is at or above the
AQL
Consumer's risk (β)
Probability of accepting a bad lot
Probability of accepting a lot when
fraction defective is below the LTPD
OC Curves for Different Sampling Plans
n = 50, c = 1
n = 100, c = 2

5/02/2014
Average Outgoing Quality
(Pd)(Pa)(N - n)
AOQ =
N
where
Pd = true percent defective of the lot
Pa = probability of accepting the lot
N = number of items in the lot
n = number of items in the sample
Average Outgoing Quality

1. If a sampling plan replaces all defectives
2. If we know the incoming percent
defective for the lot
We can compute the average
outgoing quality (AOQ) in percent
defective
The maximum AOQ is the highest
percent defective or the lowest average
quality and is called the average
outgoing quality level (AOQL)
Automated Inspection
Modern technologies
allow virtually 100%
inspection at minimal
costs
Not suitable for all
situations

5/02/2014
SPC and Process Variability

Lower Upper
specification specification
limit limit
(a) Acceptance
sampling (Some
bad units accepted)
(b) Statistical process

control (Keep the
process in control)
(c) Cpk >1 (Design

a process that
is in control)
Process mean, µ
Measurement Systems Capability
SPC Implementation Requirements
• Top management commitment

• Project champion
• Initial workable project
• Employee education and training
• Accurate measurement system
165

5/02/2014
Chapter 2:
6 Sigma
Six Sigma
A scientific and practical method to achieve

improvements in a company
Scientific:
• Structured approach. “Show me
• Assuming quantitative data. the data”
”Show me
the money” Practical:
• Emphasis on financial result.
• Start with the voice of the customer.
Where can Six Sigma be applied?

Service
Design
Management
Purchase
Administration Six Sigma

Methods Production
IT
Quality
Depart.
HRM M&S

5/02/2014
The Six Sigma Initiative

integrates these efforts
Knowledge
Management
VOC vs. VOP
Sigma Defects per

Capabilit Million % Yield
y Opportuniti
es
2 308,537 69.15%
3 66,807 93.32%
4 6,210 99.38%
5 233 99.98%
Voice of Customer 99.99966%
6 3.4
Voice of Process
The Voice of the Process is independent of the

Voice of the Customer
What’s good enough?

99% Good (3.8 Sigma) 99.99966% Good (6 Sigma)
20,000 lost articles of mail per hour 7 articles lost per hour
(based on 2,000,000/hr)
Unsafe drinking water for almost 15 1 unsafe minute every 7 months
minutes each day
5,000 incorrect surgical operations per 1.7 incorrect operations per week
week
2 short or long landings daily at an 1 short or long landing every 5 years
airport with 200 flights/day
2,000,000 wrong drug prescriptions 680 wrong prescriptions per year
each year
No electricity for almost 7 hours each 1 hour without electricity every 34
month years

5/02/2014
Not very satisfactory!
• Companies should strive for ‘Six Sigma’ quality levels

• A successful Six Sigma programme can measure and
improve quality levels across all areas within a company
to achieve ‘world class’ status
• Six Sigma is a continuous improvement cycle
Scientific method (after Box)
Data
Facts
INDUCTION INDUCTION
Theory
Hypothesis DEDUCTION DEDUCTION
Conjecture
Idea
Model Plan
Act Do
Check
Improvement cycle
• PDCA cycle
Plan
Act Do
Check
174

5/02/2014
Alternative interpretation
Prioritise (D)
Measure (M)
Hold
gains
(C)
Improve (I) Interpr

Problem (D/M/A) et
solve (D/M/
A)
Statistical background
Some Key measure
Target = µ
‘Control’ limits
+/ − 3σ
Target = µ

5/02/2014
Required Tolerance
LSL USL
+/ − 3σ
Target = µ
Tolerance
LSL USL
+/ − 3σ
Target = µ
+/ − 6σ
Six-Sigma
Tolerance
LSL USL
+/ − 3σ
1350 1350
ppm ppm
Target = µ
+/ − 6σ

5/02/2014
Tolerance
LSL USL
+/ − 3σ
1350 1350
ppm ppm
0.001 0.001
ppm ppm
Target = µ
+/ − 6σ
• Six-Sigma allows for un-foreseen ‘problems’ and

longer term issues when calculating failure error or
re-work rates
• Allows for a process ‘shift’
Tolerance
LS L USL
1.5σ
3.4 66803
0 ppm ppm ppm 3.4
ppm
+/ − 6σ

5/02/2014
Performance Standards
σ PPM Yield
2 308537 69.1%
3 66807 93.3% Current standard
4 6210 99.38%
5 233 99.977%
6 3.4 99.9997% World Class
Process Defects per Long term

performance million yield
Performance standards
First Time Yield in multiple stage process
Number of processes 3σ 4σ 5σ 6σ
1 93.32 99.379 99.9767 99.99966
10 50.09 93.96 99.77 99.9966
100 0.1 53.64 97.70 99.966
500 0 4.44 89.02 99.83
1000 0 0.2 79.24 99.66
2000 0 0 62.75 99.32
2955 0 0 50.27 99.0
Financial Aspects
Benefits of 6σ approach w.r.t. financials
σ-level Defect rate Costs of poor quality Status of the

(ppm) company
6 3.4 < 10% of turnover World class
5 233 10-15% of turnover
4 6210 15-20% of turnover Current standard
3 66807 20-30% of turnover
2 308537 30-40% of turnover Bankruptcy

5/02/2014
Key Elements for Effective

Root Cause Analysis &
Problem Solving
What we will discuss. . .
• What are problems

• How problems are communicated: CREI statement
• Types of problems and problem solving methods
• Process View of problems
• Isolating problems to their process of origin; establishing context for
Root Cause Analysis
• Levels of Root Cause investigation
• Data collection/analysis tools to apply at each level of Root Cause
investigation
• Confirming root causes before applying solutions
• Three possible solutions to each root cause
• Getting the most out of Root Cause Analysis investigations
Visual Definition of Problem

• Gap between current
condition, (what is), and
the desired performance
level, (what must be,
should be or could be)
• This gap can exist in a
process, product or system
• A problem can only be
considered to be valid if
“what should be” is
specified

5/02/2014
Where do “gaps” arise?
• Customer complaint
• Nonconforming output of a
process
• Out of control process
• Management systems not
being followed
• Safety incidents
• Environmental “releases”
• Goals not being achieved
• Can be actual, potential
or generated
Communication of Problems
CREI Problem Statement

An example of tool for communicating the gap:
• Concern: what is wrong; statement of
nonconformity
• Requirement: what should be; documented
requirement or reference to
• Evidence: data demonstrating that
something is wrong; objective evidence
observed that supports statement of
nonconformity
• (Impact): how significant is the problem
from a performance and/or cost standpoint

5/02/2014
Concern
• What is wrong?
• What is different than
what should be?
• May be recognized as a
symptom, (effect), or as
a failure condition,
(failure mode)
• Define in terms of
requirement, (language
of organization)
Requirement
• What should be
• Must be defined and valid
• Can be found in procedures,
policies, drawings,
specifications, etc.
• #1 reason problems are not
effectively solved is that
Requirement is not clearly
known or defined
• Reference where Requirement
can be found
• State as defined in
Requirement document
Evidence • Demonstrates
requirement is not
being fulfilled
• Data initially gathered
associated with problem
• Objective evidence
collected while auditing
process or system
• Must be verifiable
• Can be tangible, a
statement of admission
or observed

5/02/2014
Impact
• How big is the problem?
• How much does it cost?
• Is the customer affected?
• Is it affecting fulfillment of
organizational goals?
• Refer to effect and severity ranking
on FMEA for performance impact
• Also consider cost impact
• In the case of auditing findings:
typically, auditors do not cite Impact
as this could be viewed as subjective
• Impact should be determined by
auditee upon their review of the
audit finding
Utilizing CREI Format

• Incorporate these fields on problem solving and
nonconformance report formats to prompt
complete recording of information re: problems
• May require some investigation to identify
necessary information for completing CREI
statement, especially location and actual
statement of “Requirement”
• Critical success factor to effective problem
solving is consistent and complete
communication of problem condition
Problem Categories
and Problem Solving Approaches

5/02/2014
Types of Problems
• Simple, cause
known; “Just do it”
issues
• Complex, cause
unknown; need to
dig deeper issues
• Sometimes the
financial impact of a
problem dictates
how it will be
classified
“Just Do It” Issues

• Typically isolated, sporadic incidents
• Are easily fixed; apparent cause tends to be
known
• Often recognized during process planning
and reflected in PFMEA
• Addressed through troubleshooting,
(diagnosis and remedy) and reaction plans
on control plans, (control of nonconformity)
• Can be fixed by process owner; addressed
at process level
• Occurrence should be monitored ongoing
for cost and impact
Recognize
Troubleshooting
problem condition
Communicate
problem condition
to process owner
Diagnose problem
condition
Decide on
appropriate action
Implement remedy
Observe results of
remedy
Record condition
and remedy
Periodically review
records of
conditions for
trends

5/02/2014
“Dig Deeper” Issues

• Sometimes referred to as Chronic
• Long-term and/or complex issues
• Cause is not readily apparent, unknown
• Require in-depth investigation to identify root cause
• Addressed through root cause analysis, disciplined
problem solving and improvement process
• Source of problem typically unknown
• Cross-functional participation needed to solve
• Effective resolution requires both process and system solution
consideration
• Require management intervention via resource commitment
• When available data re: problem is limited, may be handled
as “Just do it” based on impact and/or risk
Steps in Disciplined Problem

Solving
1. Establish Team
2. Operational Problem Definition
3. Containment & Interim Actions, (if
needed)
4. Root Cause Analysis, (process & system)
5. Plan & Implement Solutions
6. Results of Solutions
7. Verification, (including independent)
8. Closure & Congratulate the Team
Problem Type Considerations

Just Do It Dig Deeper
• Reflects product or • Unanticipated
process controls conditions which occur
established when planning
the process • May also be anticipated
issues for which actual
• Management decision to level of risk is now
“live with” such conditions
based on acceptable level determined to be
of risk unacceptable
• Should be routinely • Require concentrated
evaluated for cost and investigation to
impact understand source of
• Can only be eliminated by problem and process
applying disciplined factors leading to
problem solving to problem condition to
understand true root allow appropriate
cause in order to improve solutions
process

5/02/2014
A Note about Fire-fighting!

• Fire-fighting is essentially
un-prescribed actions taken
on a process without
understanding the relation of
causal factors and process
output
• Fire-fighting is dangerous as
these actions tend not to be
specifically focused to a
particular cause
• The resulting impact of fire-
fighting is typically not
known ahead of time
• Therefore, chaos is
introduced into the process
• A very high-risk approach to
problem solving!
Problem Type Considerations

Problem Type Process of Method Considera-tions
Origin
Just do it Known Troubleshooting; Seen before; can live

rework with impact when
problem recurs
Dig Deeper Unknown Root cause analysis Data-driven

investigation to
determine actual
factors causing
problem condition
Unknown Fire-fighting Taking action
possibly on wrong
process; not using
data to confirm root
cause
Prioritize Problems
• Most organizations should only be
actively working on 3-5 disciplined
problem solving efforts, (Dig
Deeper issues), at a time to balance
the use of resources and get the most
effective solutions; (no one person
should be working on more than 2 Dig
Deeper teams at any given time)
• Impact portion of CREI statement
facilitates prioritization of problems for
allocation of problem solving resources
• Management is responsible for
establishing the priority

5/02/2014
Process View of Problems
The Secret to Solving Problems

• The source of every problem is a process: typically the gap is
found in the output of the process
• The cause of every problem is one or more process factors not

behaving as they should
• Understanding the relationship between process factors and

process outputs is important to effective problem solving
• Data about the process and the problem is required to gain

enough understanding to effectively solve any problem
• The result of any problem solving effort is increased knowledge

about processes and their outputs
Components of Process
Environment Evaluation
(space, layout, etc.) (plan, gages, etc.)
Input Process steps Actual Output

(Methods)
(Materials) (Desired outcome:
targets, goals, specs)
Equipment People
(selection, (training, skills)
Maintenance, etc.)
Management Policies & Practices

5/02/2014
What are the Process Factors?

Processes are mainly Other factors which
influenced by: influence processes
• Man include:
• Material • Measurement
• Machine • Management System,
• Methods (policies including
SOPs, targets,
• Mother Nature, operational decisions)
(environment)
• Money
• Other?
Process View
Products/Services = output of producing Processes
Producing Processes to accomplish Plans
Planning Processes apply System

to fulfill customer requirements
System Processes = Policies, Objectives & Practices

(how an organization does business)
Main Functions of Problem Solving

• Define Gap between “what
is” and “what should be”
• Identify process of origin
from which gap is
originating
• Study the process of origin
to determine which process
factor(s) are causing the
gap
• Analyze the relationship
between process causal
factors and system factors
to identify root cause

5/02/2014
Getting to the Process of Origin
• Where was the problem found?

• Where is the first process the problem condition could occur?
• Go to these and any processes in between to collect data
recognizing where the problem is actually first observed; this
is the process of origin!
• Use a process flow diagram to make this investigation visual.
Process Mapping Process

Prepared by: C. Fisher 11/1/2002
Identify inputs
Identify last step of Identify who
Select Process to Identify output of needed for process
process which receives output and
map process and who supplies
creates that output their requirements
these
Sequence process
Combine Brainstorm process
steps between first
Clarify any process brainstormed steps which occur Identify first
and last process
step ideas which process steps for between first and process step and
step to reflect
are unclear duplication/similar last identified trigger input
current process
ideas process steps
flow
Review flowchart Review process Revise process Analyze process Assess feasibility of
for correct structure map with process map based on map to identify and establish goals
(use 8 point owners for feedback from improvement for potential
checklist) accuracy process owners opportunities improvements
Measure impact of Update process Establish plan for

implemented map to reflect implementing
improvements improvements improvements
Is/Is Not Analysis

• Also known as Stratification Analysis
• Provides further detail about the problem so a
complete operational definition of the
problem can be formulated.
• Used at this stage as well as in applying
interim/containment actions and
implementing/verifying permanent actions.
• “Splitting the dictionary” or “20 questions to
the answer” demonstrates this idea of
problem convergence

5/02/2014
Use Data to determine

• What is the problem? – define the problem condition such that
anyone could recognize it; basis for data collection about the
problem
• Where is the problem occurring? – which processes,
customers; also, where on the output is the problem condition
observed?
• Who knows about the problem? – who initially identified the
problem? Who else has seen this problem? Who is involved in
the process steps reflected in the process flow?
• When did the problem begin? – timeline associated with when
the problem was seen; can be applied even for ongoing
problems
• How big is the problem? – how much output is affected?
• Narrows the problem focus to isolate the problem to its process
of origin
• Data is collected to demonstrate answers to these questions
Is/Is Not Analysis Worksheet

Focus Aspect Data to Where to How to Results – Results – Comments
Collect Collect Collect IS IS NOT
What? Problem Refer to
condition requirement
Where? Geographically See process

flow
Where? On output Concentration Refer to

diagram problem
condition
When? First seen Refer to

timeline
Seen before?
Days, shifts,
time
Who? Identified Interview

problem
Involved in Interview Refer to
related process flow
processes
Customers
How Quantity Containment
Applying Is/Is Not Analysis

• Clarify aspect – what question needs to be answered to
obtain a better understanding of the problem
• Identify what data to collect that would assist in answering
the question
• Determine where that data can be obtained
• Decide how to go about collecting the data; what
tools/methods to apply
• Go collect the data
• Review and analyze the data to draw a conclusion re:
questions being posed
• This is an important step in Root Cause Analysis as the
results of this investigation provide a context for the root
cause investigation
• By conducting Is/Is Not Analysis, it is also possible to
determine if further investigation can take place at this time

5/02/2014
Components of Problem’s
Operational Definition
• Basis for root cause investigation
• More detailed version of CREI statement based on
what was learned from Is/Is Not
• Indicate process from which problem
originated/generated
• Indicate direction of problem related to requirement
• Define extent of problem
• Possibly isolates problem to a certain timeframe
• Include refined information re: impact
• Problem statement must be clear, concise and
understandable by anyone
A Root Cause is. . .
A process factor which directly defines

the reason for the problem when it is
present and is having an influence on
the process and its output.
4 Levels of Root Cause

Defect/Detection Cause = Product level
Direct Process Cause = at Process of Origin
Actual Root Cause = previous process factors

contributing to Process Root Cause, (planning)
System Root Cause = management system

policy/practice contributing to Actual Root Cause

5/02/2014
Dig! How Deep?

• Management decides
on depth of root
cause investigation
through the
establishment of
SMART goals for
each problem solving
effort.
Problem Solving Goals

• Define problem’s
boundaries/depth of Effective Problem Solving is
solutions based on
• Identify right people to SMART Goals:
solve problem
• Establish measures of end • Specific
results • Measurable
• Develop plan of how to • Agreed upon by team as
accomplish the goal attainable
• Tie problem solving goals • Relevant to organization
and results-oriented
to organizational
objectives/targets • Timing defined
• Provided to team by
Management
Root Cause Analysis

• Systematic investigation
of a process to identify
the root cause of the
gap, and take corrective
action to eliminate the
gap and keep it from
occurring again in the
future
• A structured investigation
that aims to identify the
true cause of a problem,
and the actions necessary
to eliminate it.

5/02/2014
Process Cause vs. System Cause

Process Cause System Cause
• What factor of the process • Addresses how the
of origin is triggering the management system
undesirable output allowed the process to
• What other processes and become out of control
their factors are causing the • Relates process factor
trigger? causes to “weaknesses” in
• Relates product output, management systems
(symptom), to process policies/practices
parameters, (causes)
P r o c e s s
R o o t C a u s e A n a l y s is I d e n t if y p r o c e s s
fr o m w h ic h
p r o b le m o r ig in a t e d
D is c ip lin e d P r o b le m
4 /8 /2 0 0 7
S o lv in g
R e v ie w d a ta fr o m
o p e r a t io n a l
d e fin itio n ,
c o n ta in m e n t a n d
in t e r im a c t io n
I d e n t if y p o t e n t ia l
c a u s e s
c o n t r ib u t in g to th e
p r o b le m
D e v e lo p p la n t o
t e s t if p o t e n t ia l
c a u s e a c t u a lly
le a d s t o p r o b le m
C o n d u c t te s t a n d
c o lle c t d a t a
A n a ly z e d a t a f r o m
te s t
D o e s p o t e n t ia l
S e le c t o th e r c a u s e d ir e c t ly
N o
p o t e n t ia l c a u s e s le a d to p r o b le m
c o n d it io n ?
Y e s
I d e n t ify p o s s ib le
C a n c a u s e b e
a c t io n s t o m o n it o r
N o c o n t r o lle d o r
p r o c e s s fo r
e lim in a t e d ?
p r o b le m c o n d it io n
Y e s
I d e n t if y p o s s ib le
a c t io n s f o r e it h e r
c o n t r o llin g o r
e lim in a tin g c a u s e
S y s t e m
I d e n t if y
R o o t C a u s e A n a ly s is m a n a g e m e n t
p o lic ie s r e la t e d to
p r o c e s s f r o m
D is c ip lin e d P r o b le m w h ic h p r o b le m
4 /8 /2 0 0 7 o r ig in a te d
S o lv in g
R e v ie w e x is t in g
p o lic ie s fo r e x is t in g
c o n t r o ls
I d e n t if y p o s s ib le D o c u r r e n t p o lic ie s
m a n a g e m e n t d e f in e c o n t r o ls t o
N o
p o lic y c o n t r o ls t o p r e v e n t t h e c a u s e o f
a d d r e s s c a u s e t h e p r o b le m ?
Y e s
I n v e s t ig a te if t h e s e
c o n t r o ls a r e in
p la c e
Id e n tif y h o w t h e s e
c o n t r o ls a n d / o r C o n t r o ls
N o
p o lic ie s c a n b e w o r k in g ?
c h a n g e d
Y e s
A n a ly z e w h y
c o n t r o ls a r e n o t
w o r k in g a t t h e
p r o c e s s w h e r e
p r o b le m o r ig in a te d
I d e n t if y o t h e r
p r o c e s s e s a f fe c t e d
b y t h e s e p o lic ie s

5/02/2014
Root Cause Analysis Levels

Level Root Cause Consideration Tools Other
(Wide)
(Deep)
Product Defect/Detection Condition of Control Barrier What other

cause controls to detect Analysis products have
problem similar controls?
Process Direct process cause, Factors at process Fishbone, What processes

(trigger at process of of origin triggering (cause & have similar
origin problem, (5Ms) effect) trigger cause?
Plan Actual root cause, Linkage to 5 Why with What other

(led to trigger cause) planning Hypothesis processes
processes that testing affected?
trigger cause
System “weakness” in mgt. Linkage of mgt. System Cause Other affected

policies or practices system to actual Analysis mgt. policies
cause
Control Barrier Analysis

(Defect/Detection Root Cause)
• How did the problem • Were the planned
escape the process controls in place?
and/or organization? • Were the planned
• Was the problem controls working?
anticipated in advance? • What is the capability
• Were controls defined of these controls?
to recognize and • Assists in identifying
contain the problem? appropriate interim
• At which process are actions as well as
the planned controls identifying the
applied? defect/detection root
cause
Control Barrier Analysis Worksheet

Process Condition Control Status Capability Observations Actions
Other Opportunities:

5/02/2014
Results of Control Barrier Analysis

• May recognize missing controls or controls not working as
planned
• Interim actions represent solutions to addressing these
concerns but should not be accepted as the permanent
solution
• When the results of this analysis uncover additional
problems, refer these to the team champion for direction
on addressing
• Team’s main focus at this point is to implement some type
of control to protect downstream processes from
continuing to experience the problem
• Solutions based on this level of “root cause investigation”
mainly are reactive in nature; they only improve our ability
to detect the problem condition but don’t typically do
anything about addressing the root cause!
Direct Process Cause

• Relates one or more factors of the affected process,
(process of origin), not “behaving” as required to
obtain the desired output result at that process
• Use Cause & Effect diagram, (fishbone technique)
• Direct process causes, (trigger causes), are the
starting point for identifying root cause
• Some action may be required to address the direct
process/trigger cause but actions should not be
taken until actual root cause is known
Cause & Effect Diagram

• Apply to problem’s
process of origin
• Gap is head of fish
• Major cause categories
– 5M’s
• Potential causes
brainstormed are
process factors existing
at the problem’s
process of origin
• Define potential causes
specifically
• When confirmed, these
will be known as direct
process/trigger causes

5/02/2014
Fishbone Diagram
Fishbone Process
• Involve personnel from process of origin in brainstorming
of potential causes at the process of origin triggering the
problem
• Develop a sketch/list of the process factors, (man,
material, machines, methods, mother nature), related to
the process of origin
• After brainstorming, review each identified cause to
establish:
• If the cause is actually a factor at the process of origin
• If the cause makes sense based on the operational definition of
the problem
• Prioritize remaining causes as to their possible
contribution to the problem condition
• Develop hypothesis test to evaluate each potential cause
at the process of origin
Direct Process Root Cause Investigation

Plan & Results Process of Origin:
Potential Related Feasible Priority Method of Results of confirmation

Causes to based on to confirmation
process? operational confirm
definition?
Confirmed causes to investigate via 5 Why Analysis:

5/02/2014
Problem Understanding Tools

(especially useful in identifying system causes)
• Task Analysis – reviews process in detail; helpful for

operator dependent process
• Change Analysis – identifies differences; extension of Is/Is
Not analysis; expands on application of timeline
• Both these tools must be applied with a location context,
(process of origin)
Task Analysis Worksheet

Steps Who Required Actions Component Tools Remarks/Questions
Change Analysis Worksheet

Change Factor Difference/Change Effect Questions to Answer
What (conditions,
activity, equipment)
When (occurrence,
status, schedule)
Where (physical
location,
environmental
conditions, steps of
procedure)
How (work practice,
omission, extraneous
action, out of
sequence, poor
procedure)
Who (personnel
involved, supervision)

5/02/2014
Actual Root Cause

• Explains why trigger cause/condition exists at the
process of origin of the problem
• Typically found in previous “planning” processes
• Many problems have multiple causes
• Usually only one over-riding cause that when addressed,
can significantly reduce the problems impact on the
organization
• Very complex problems may have interacting causes but
these are typically viewed as isolated problems that only
repeat infrequently, (often managed as Just Do It), until
resources allow necessary time to discover interaction
through data collection, analysis and experimentation
5 Why Analysis
• Ask “Why does this happen?” for
each identified process cause from
Cause & Effect diagram
• Differentiates between process,
(direct) cause and underlying root
cause
• Each level of causes identified in 5
Why analysis must also be
confirmed via testing in order to
verify root cause
• Deeper levels of 5 Why Analysis
which get into Planning processes
will require interview-type data
collection
5 Why Analysis Worksheet

Process Plan/Data Results 2nd Plan/Data Results 3rd Plan/Data Results 4th Plan/data
of Origin to confirm level to confirm level to confirm level to confirm
Cause Cause Cause Cause

5/02/2014
Test Potential Root Causes

• Validating cause
“guesses” by
collecting and
analyzing data
• Test under controlled
conditions
• Turn the problem on
and off by
manipulating the
suspected cause
Hypothesis Testing
• Design hypothesis and select methods for
testing hypothesis - state how potential cause
could result in described problem; decide what data
to collect that would prove potential cause; establish
acceptable risk of decision outcome; determine
sample size; develop action plan for study
• Prepare to test hypothesis - organize and prepare
materials required to conduct study; collect data
during study
• Analyze results of test - analyze data using
appropriate statistical tools, (t, F, Chi-squared tests)
• Interpret results - conclusions from study; does
data establish potential cause as reason for problem?
Root Cause Analysis Plan

• Identify causes to be investigated
• What data supports each cause?
• Can cause be introduced and removed to
confirm presence/absence of problem?
• What tests will be performed to confirm root
cause?
• What is the statistical confidence of these tests?
(i.e. how much data is needed?)
• Results of tests recorded and analyzed with
conclusions drawn

5/02/2014
System Causes
• What in the system allowed this problem/cause to
occur
• Identifies why the process root causes occurred
based on current management policies/practices
• Often not readily measurable
• Data obtained through interview
• By identifying system causes, systemic improvement
can be made in order to prevent recurrence of
problem in other similar processes
• Typically addressed once process root causes of
problem are known and confirmed
System Cause Analysis Worksheet

Operational Definition:
Process of origin cause:
Process root cause:
Which management system process is the process root cause related to?
Who is responsible for this management system process?
What documentation/policies are available describing actions and controls for this management
system process?
Does this documentation/policy recognize the possibility for this problem to occur?
Are there any current management system controls in place to prevent or detect this problem?
Has this management system process been associated with previous problems?
What other processes within the organization are driven by this management system process?
Possible Management System Level Solutions:

1) Create new policy
2) Change existing policy
3) Reinforce/re-apply current policy
Problem Solutions
• There are always at least 3 Possible Solutions Matrix

possible solutions related to Root Confirmed Eliminate Control Detect Gap
each level of cause Cause(s)
Defect:
• Therefore, at least 12
possible solutions could be
Direct:
identified for a problem
investigation if all levels of
cause are investigated! Actual:
• Management provides
System:
solution selection criteria as
basis for evaluating possible
solutions

5/02/2014
3 Possible Solutions
• Eliminate root cause – preventive control; often

referred to as error-proofing; eliminates causal factor
leading to problem condition
• Control root cause – process detective control;
implement actions to monitor cause condition so
action can be taken on process factor before problem
occurs
• “Do nothing” – reactive control; continue
monitoring for problem condition; defect detection
solution; may be required when root cause can’t be
eliminated or controlled economically or technically;
this solution may include accepting interim action as
permanent solution
Solution Selection
• Allow brainstorming of possible solutions at all levels
of confirmed causes and the 3 possible categories of
solutions
• Then apply solution selection criteria provided by
management to evaluate each possible solution as
well as refine the brainstormed ideas
• Have data available re: actual costs associated with
problem, (initial impact, revised impact based on
data collection/analysis, anticipated future impact if
no action is taken)
CRITERIA MATRIX
SOLUTIONS
A B C D E n*
CRITERIA
1
MUSTS 2
n*
WANTS 2
n*
RATING TOTALS
* reflects any number of variables that are appropriate to include in the analysis.

5/02/2014
Implementing Solutions
• Actions to eliminate and Change Management

control causes require Tools
change • FMEA
• Change management tools • Risk assessment
should be applied when • Resource planning
implementing solutions
• Contingency planning
• Training
• Evaluation
• Verification
P la n , Im p le m e n t B r a in s to r m
p o s s ib le s o lu t io n s
fo r e a c h c o n f ir m e d
& V e r if y S o lu t io n s r o o t c a u s e
P e r m a n e n t
s o l u t io n
im p le m e n t a tio n
4 /8 /2 0 0 7
E s t a b l i s h s o l u t io n
s e le c t io n c r ite r ia
E v a lu a te r e s u lt s o f
p e r m a n e n t
s o l u t io n
E v a lu a te p o s s ib le
s o lu t i o n s v s .
s o l u t i o n c r it e r i a
R e m o v e in t e r im
a c t io n s
D e v e lo p a c t i o n
p la n t o im p le m e n t
s e l e c t e d s o lu t i o n s
T e a m v e r i f ic a t i o n
o f s o lu t i o n v s .
g o a ls
E v a lu a t e s o l u t i o n
r is k s a n d im p a c t
o n o th e r
p r o c e s s e s
I n d e p e n d e n t
v e r if ic a t io n o f
p r o b le m s o lv i n g
e f fo r t
D e v e lo p
c o n tin g e n c y p la n
f o r s o l u t io n s
F in a liz e p r o b le m
s o lv in g r e p o r t ,
le s s o n s le a r n e d
E s t a b l i s h s o l u t io n
e f fe c t iv e n e s s
m e a s u r e s
T e a m c e le b r a tio n
a n d d is b a n d in g o f
p r o b le m s o lv i n g
t e a m
T r ia l p l a n f o r
s o lu tio n
im p le m e n ta t io n
E v a lu a t e t r ia l p l a n
r e s u lt s
R e v is e s o lu tio n
im p le m e n ta t io n
p la n a s n e c e s s a r y
Other Opportunities
• Identified typically while collecting data for Is/Is Not Analysis,

Root Cause investigation/confirmation, solution evaluation
• Record these other problems/opportunities
• Share these problems/opportunities with team champion to
get direction on how to address: (change scope of current
problem solving effort to include; management assigns
another team to address)
• Don’t allow these other opportunities to distract from the
focus of the problem solving effort
• These Other Opportunities become the “Bonus” of an
effective problem solving effort

5/02/2014
A Key Outcome of Every Problem

Solving/Root Cause Investigation. . .
Expansion of Knowledge
Failure Modes & Effects Analysis

(FMEA) – A Tool for Cataloging Problems
Process Potential Potential Potential Current
Function Failure Failure Failure Product &
Requirements Modes Effects Causes Process
Controls
Process of Technical Symptom Process Interim
origin definition of factors = root actions
problem causes
Management’s Role
System Each Problem
• Establish problem solving • Appoint Team Champion
culture • Define SMART goals for
• Provide problem solving problem solving effort
process • Provide resources and time
• Ensure training of all to support problem solving
personnel in problem team
solving process and related • Establish solution selection
tools criteria
• Prioritize/categorize • Authorize Team Plan as
problems based on contract for problem solving
magnitude/risk effort
• Audit/review effectiveness • Periodically review progress
of problem solving system of problem solving teams

5/02/2014
Problem Solving Culture

• Problem solving is a value-added process
• Problem solving supports improvement of every
aspect of the business
• Time should be dedicated to problem solving on a
daily basis
• Everyone in the organization is involved in problem
solving
• Use problem solving survey to measure effectiveness
of problem solving system
Quality Improvement Strategies

Problem Solving Survey – Short Version
This tool can be used to evaluate your organization’s problem solving system. The survey can be
administered to any employee to gain an overall understanding of perceptions regarding this key
process within your business. Continual improvement of the problem solving process can be measured
based on conglomerate results of this survey, (can be re-administered repeatedly to evaluate progress).
Each response scored 3 or 5 should have related evidence indicated to support.
Scoring: 1 = no evidence currently exists to demonstrate this

3 = evidence exists to demonstrate this, but improvement potential
exists
5 = this aspect of our problem solving system is “world class”, (i.e.
would want others to benchmark ours)
NA = not applicable; unable to respond
Culture:
Question Score Evidence/Observations
1 Is problem solving viewed as a value-added
process in your organization?
2 Are problem solving behaviors/expectations
defined and communicated?
3 Are resources, (e.g. time), allocated
specifically in support of problem solving?
4 Is problem solving used throughout the
organization in all areas and at all levels?
5 Are the top 3-5 problem solving efforts known
by all employees throughout the organization?
Chapter 2 :
5 M Diagram

5/02/2014
Objective
In This Module We Will….
• Define a Cause and Effect diagram

• Understand the elements of C&E analysis
• Understand why and when to use C&E diagrams
• Understand the importance of team involvement
when brainstorming
• Workshop on project team’s C&E Diagram
Cause & Effect Diagram

• The Cause and effect diagram is also called:
• Fishbone Diagram-because of the way it looks
• Ishakawa Diagram for the inventor, Dr. Kaoru Ishakawa.
Main Category
Problem/
Desired
Improvement
Cause
Root
Cause
What is a Cause and Effect Diagram?

• A visual tool to identify, explore and graphically
display, in increasing detail, all of the suspected
possible causes related to a problem or condition to
discover its root causes.
• Not a quantitative tool
Main Category
Problem/
Desired
Improvement
Cause
Root Cause

5/02/2014
Why Use Cause & Effect Diagrams?

• Focuses team on the content of the problem
• Creates a snapshot of the collective knowledge of team
• Creates consensus of the causes of a problem
• Builds support for resulting solutions
• Focuses the team on causes not symptoms
• To discover the most probable causes for further analysis
• To visualize possible relationships between causes for any
problem current or future
• To pinpoint conditions causing customer complaints, process
errors or non-conforming products
• To provide focus for discussion
Product/Manufacturing
Man
Machine Methods
Five Key
Sources of
+ Environment
Variation
Materials Measurement
Use cause and effect diagram to single out variation

sources within the “5M’s + E”
Transactional/Service
People
Policies Procedures
Five Key
Sources of
Variation
+ Environment
Place Measurement
Use cause and effect diagram to single out variation

sources within the “4P’s + M&E”

5/02/2014
Fishbone - Cause and Effect Diagram

Causes Effect
Main Category
Problem
Cause
Root
Cause
Shows various influences on a process to identify

most likely root causes of problem
Constructing a C&E Diagram

Materials Methods
Problem/
Maintenance
Machinery Manpower
Brainstorm to determine root causes and
add those as small branches off major bones
Fishbone Diagram Example
Fishbone diagram sourced from GOAL/QPC Black Belt Memory Jogger published 2002

5/02/2014
Same Example More Detail
Physical C&E Construction
• C&E Fishbone diagrams can be constructed two ways:

• Paper and pen
• Usually more effective when working in a team
• May take multiple sheets of flip chart paper
• Many teams find it helpful to do the flip chart method first because it
lends itself to group dynamics. Everyone can see and participate
easier.
• Minitab software
• Very helpful when sharing diagram with an audience outside of your
team
C&E Workshop
In Project Teams, complete the following items:
1. Determine the problem or “head’ of the fishbone
2. Determine if your process is Transactional/Commercial or
Product/Industrial
3. Create a Cause & Effect (C&E) Fishbone diagram using:
- 4 P’s and M & E (Transactional process)*
- 5 M’s and E (Product process)*
* Use the headings (Ps and Ms) as guidelines. Customize to better describe the process

5/02/2014
Chapter 3:
Process Diagram
What is in a Functional Block Diagram?

• A function block diagram describes a function
between inputs and outputs and should describe
the system in one picture.
• What should it include

• Show All major system components
• Interfaces to the outside world
• Interfaces between subsystems
• Clearly identify power, data, and structural interfaces
• Should answer how the mission statement is met
• Easy to read
Pick and Choose

• The following are FBD for progressively more complex
systems. All contain strengths and weaknesses in conveying
system level information. Pick ideas which would work well in
describing your project.
• The Final FBD is a poor example due to it’s complexity for this
application. Use this as an example of what not to do as it is
too hard to read.

5/02/2014
DOE - (design of experiments)

will help us identify...
A1 A2
factors which shift the average
B1
B2 factors which affect variation
C2 factors which shift the average and affect

C1
variation
D1=D2
factors which have no effect

Measure the Process Establish the
Controllable Inputs
performance
X1 X2 X3 baseline
Quality
Characteristics:
Inputs: Outputs
LSL USL
Raw Y1, Y2, etc.
Materials,
components, The Process
etc.
S O D R
Process Actions
Potential FailureMode Potential FailureEffects E Potential Causes C Current Controls E P
Step/Input Recommended
V C T N
LoadDMF/DMF Foolproofthisprocess
OperatorCertification/Process
LoadAccuracy Mischargeof DMF Viscosityout ofspec 7 SOPnotFolowed 5 5 175 usinginputfromTQL
Audit
Team
Steamto IncludeDailysign-offof
DICY/Scale ScaleNot Zeroed MischargeDMF 3 FaultyScale 2 None 9 54 ScalefuntioninShift
Accuracy set-upverification.
LoadDMF/DMF MaintenanceProcedure(SOP
LoadAccuracy Mischargeof DMF Viscosityout ofspec 7 EquipmentFailure 2 3 42
5821)/VisualCheck
Steamto
N1 N2 N3
DICY/Scale Scale>0 LowDMFCharge 3 Water inJacket 2 Visual CheckofJacket(SOP5681) 4 24
Accuracy
Steamto
DICY/Scale ScaleInaccurate HighDMFCharge 3 TankHangingUp 2 Visual Check(SOP5681) 4 24
Accuracy
Uncontrollable Inputs
K e y O u tp u ts :
1
V a ri a b le H o w M eas u red W hen M eas u red
2
Analyse the Process

3
N o is e V a r i a b le s: V a ri a b le H o w M eas u red W hen M eas u red
1
2
3
Controllable Inputs
4
5
C o n tr o l la b l e In p u ts V a ri a b le H o w M eas u red W hen M eas u red
X1 X2 X3
1
2
3
4
5
O v e r a l l S a m p li n g P l a n :
Quality
Characteristics:
Outputs
LSL USL
Inputs:
Y1, Y2, etc.
Raw
Materials,
The Process
components,
etc.
Run Temperature Pressure
1 Hi Hi
2 Hi Hi
C a p a b ility u s in g P o o le d S ta n d a rd D e v ia tio n
X b a r a n d R Ch a rt Ca p a b ility Histo g ra m 3 Lo Hi
3 .0
M eans
4 Lo Hi
2 .5 U C L =2 .5 6 8
M U =2 .3 7 6
L C L =2 .18 3
2 .0
1.5 1.5 2 .5 3 .5
S ubgr
0 .9
1 2 3 4
U C L =0 .9 6 2 1
No rm a l P ro b P lo t 5 Hi Lo
Ranges
N1 N2 N3
0 .6
R =0 .5 16 2
0 .3
L C L =0 .0 7 0 2 7
6 Hi Lo
0 .0
1.5 2 .5 3 .5
L a st 4 S u b g ro u p s Ca p a b ility P lo t
P ro c e ss To le ra n c e 7 Lo Lo
3 .0 1.8 3 17 5 2 .9 19 5 8
Values
2 .5 C p : 2 .7 6 I I I
C PU : 2 .9 9 I I I
2 .0
1.5
CP L : 2 .5 3
C p k : 2 .5 3
1
Sp e c if ic a t io n s
4
8 Lo Lo
1 2 3 4 St D e v : 0 .18 13 0 6
Su b g ro u p N u m b e r

5/02/2014
Three Factor Design

Improve the Process
PrimWdth
Nip FPM
Controllable Inputs
ScrewRPM
X1 X2 X3
Quality
X Characteristics:
Outputs
LSL USL
Inputs:
X
Y1, Y2, etc.
Raw
Materials,
The Process
components,
etc.
X LSL USL
N1 N2 N3

Error
Control the Process
Controllable Inputs
Proofing X1 X2 X3
Quality
Characteristics: USL
Outputs LSL
Inputs:
Raw Y1, Y2, etc.
Materials,
components, The Process
etc.
Work
Instructions Check
5 C’s Lists
N1 N2 N3
Analyze
• Investigate source of variation (Special cause / Common
causes)
• Special cause variation are the one off, occasional and

obvious cause of a process / quality problems.
• Common cause variation are the day in day out causes of

process problems, because the process is not stable enough,
they are hidden (these form 80% of process problems)
• Conventional non-conformance management systems seek

to solve special cause variation (e.g. concessions) - but
these only represent 15 - 20% of the total variation.
• 6 Sigma addresses all variation.

5/02/2014
Chapter 4:
method CEDAC
CEDAC Approach
• CEDAC = cause-and-effect diagram with additional cards.

• 3 conditions must exist for continual improvement to occur.
• A reliable system (standardized and reliable)
• A favorable environment (favorable to improvement)
• Practicing as teams (Total Quality is performed by teams. Teams must
practice)
CEDAC Diagram
http://syque.com/improvement/Cause-Effect%20Diagram.htm

5/02/2014
10-Step Process of Implementation

• Draw Basic Diagram
• Select the focus of improvement efforts
• Name project leader
• Establish measurement method
• Establish improvement goal and date
• Format effect side of the diagram
• Collect fact cards for the cause side (each team member fills
out cards with their ideas)
• Collect improvement cards
• Implement and test ideas
• Select cards for standardization
Chapter 5:
Workshops

SPC For Operators

Uploaded by

Copyright:

Available Formats

You might also like

SPC For Operators

Uploaded by

Document Information

Original Description:

Original Title

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

SPC For Operators

Uploaded by

Copyright:

Available Formats

5/02/2014

Quality Improvement and Statistics

Quality means fitness for use

Quality Improvement and Statistics

Alternatively, quality improvement is also

Powered by HERA CONSULTING 1

Quality Improvement and Statistics

• Statistical process control is a

Statistical Process Control

Powered by HERA CONSULTING 2

Statistical Process Control (S.P.C.)

• This is a control system which uses

• It is an effective method in preventing

What does S.P.C. mean?

Powered by HERA CONSULTING 3

What does S.P.C. mean?

What does S.P.C. mean?

Powered by HERA CONSULTING 4

Man Machines Material

Management Methods Mother Nature

• S.P.C. is statistical analysis of

The Aim of S.P.C. - Detection Strategy

Powered by HERA CONSULTING 5

The Aim of S.P.C. - Detection Strategy

The Aim of S.P.C. - Prevention Strategy

The Aim of S.P.C. - Prevention Strategy

Powered by HERA CONSULTING 6

The Benefits of S.P.C.

• Assesses the design intent.

Process Element Variable Examples

Powered by HERA CONSULTING 7

• The process can only be termed

• Its variability is stable over a long

Powered by HERA CONSULTING 8

Process Control Charts

1 36.36 11 36.37 21 36.34 31 36.35 41 36.36

Powered by HERA CONSULTING 9

Data Interpretation – Tally Chart

36.38 • The tally chart

Tally Chart - Frequency

Tally Chart - Information

• The tally chart gives us further information:

Powered by HERA CONSULTING 10

0 36.31 36.32 36.33 36.34 36.35 36.36 36.37 36.38 36.39

0 36.31 36.32 36.33 36.34 36.35 36.36 36.37 36.38 36.39

• The bell-shaped pattern is fairly typical of

Powered by HERA CONSULTING 11

Population and Sampling Distributions

-3σx -2σx -1σx x +1σx +2σx +3σx

Powered by HERA CONSULTING 12

• A process that is operating with only

Powered by HERA CONSULTING 13

Powered by HERA CONSULTING 14

Central tendency Variation Shape

Weight Weight Weight

present, the Prediction

Powered by HERA CONSULTING 15