3.

Statistical process
control
Introduction
Statistical process control (SPC) is a powerful collection of problem‐
solving tools useful in achieving process stability and improving
capability through the reduction of variability.
7 major tools are:
1. Histogram or stem‐and‐leaf plot
2. Check sheet
3. Pareto chart
4. Cause‐and‐effect diagram
5. Defect concentration diagram
6. Scatter diagram
7. Control chart
Chance and assignable causes of
quality variation
Chance cause of variation:
• In any production or service process, regardless of how well designed or carefully
maintained it is, a certain amount of inherent or natural variability will always
exist.
• A process that is operating with only chance causes of variation present is said to
be in statistical control. In other words, the chance causes are an inherent part of
the process.
Assignable causes of variation:
• Other kinds of variability may occasionally be present in the output of a process.
• This variability in quality characteristics usually arises from three sources:
improperly adjusted or controlled machines, human variability including operator
errors, or defective raw material.
• Such variability is generally large when compared to the background noise, and it
usually represents an unacceptable level of process performance.
• A process that is operating in the presence of assignable causes is said to be an
out‐of‐control process.
Chance and assignable causes of
quality variation
Process control
• Processes will often operate in the in‐control state for
relatively longer period of time. However, no process is
truly stable forever, and, eventually, assignable causes
will occur, seemingly at random, resulting in a shift to
an out‐of‐control state where a larger proportion of the
process output does not conform to requirements.
• A major objective of statistical process control is to
quickly detect the occurrence of assignable causes of
process shifts so that investigation of the process and
corrective action may be undertaken before many
nonconforming units are manufactured.
Control charts
• The control chart is an online process‐monitoring technique
widely used for this purpose.
• Control charts may also be used to estimate the parameters of
a production process, and, through this information, to
determine process capability.
• The control chart may also provide information useful in
improving the process.
• Finally, remember that the eventual goal of statistical process
control is the elimination of variability in the process. It may
not be possible to completely eliminate variability, but the
control chart is an effective tool in reducing variability as much
as possible.
Statistical basis of the control charts
• The control chart is a graphical display of a quality
characteristic that has been measured or computed
from a sample versus the sample number or time.
Statistical basis of the control charts
• The chart contains a center line that represents the average value of
the quality characteristic corresponding to the in‐control state. (i.e.,
only chance causes are present.) Two other horizontal lines, called
the upper control limit (UCL) and the lower control limit (LCL), are
also shown on the chart.
• These control limits are chosen so that if the process is in control,
nearly all of the sample points will fall between them.
• As long as the points plot within the control limits, the process is
assumed to be in control, and no action is necessary. However, a
point that plots outside of the control limits is interpreted as
evidence that the process is out of control, and investigation and
corrective action are required to find and eliminate the assignable
cause or causes responsible for this behavior.
Statistical basis of the control charts
There is a close connection between control charts and hypothesis testing.
H0: Process is under control
H1: Process is out of control

𝑥
Upper natural Assignable cause of
variation limit variation signal

Upper control limit

99.73
99.73

%
%

Process mean
Process mean
under control

Lower control limit t

Lower natural
variation limit
Rational subgroups
• A fundamental idea in the use of control charts is the collection of sample
data according to what Shewhart called the rational subgroup concept.
• To illustrate this concept, suppose that we are using an control chart to
detect changes in the process mean. Then the rational subgroup concept
means that 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.
• Two general approaches to constructing rational subgroups are used.
1. Each sample consists of units that were produced at the same time (or as closely
together as possible). Ideally, we would like to take consecutive units of production.
2. Each sample consists of units of product that are representative of all units that
have been produced since the last sample was taken. Essentially, each subgroup is
a random sample of all process output over the sampling interval.
The feedback principle

PROCESS MEASURE GOAL

ADJUST COMPARE
General model for control charts
Let w be a sample statistic that measures some quality
characteristic of interest, and suppose that the mean of
w is μw and the standard deviation of w is σw. Then the
center line, the upper control limit, and the lower control
limit become

This type of control charts are often called Shewhart

control charts.
Control charts
• The control chart is a device for describing in a precise manner
exactly what is meant by statistical control; as such, it may be
used in a variety of ways. In many applications, it is used for
online process monitoring or surveillance.
• The most important use of a control chart is to improve the
process. We have found that, generally,
1. Most processes do not operate in a state of statistical control, and
2. Consequently, the routine and attentive use of control charts will assist
in identifying 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 will only detect assignable causes. Management,
operator, and engineering action will usually be necessary to eliminate
the assignable causes.
 Improved process using control
charts

Out of Control In Control Improved

UCL


Target value of
specification
LCL

Time
Process improvement using control
charts
Input Output
Process

Measurement
system

Verify and follow-up Detect assignable cause

Implement corrective action Identify root cause of problem

Types of control charts

Variables control charts

(continuous variables)

Control charts
p
np
Attributes control charts
c
u
Choice of control limits
• Specifying the control limits is one of the critical decisions that
must be made in designing a control chart.
• By moving the control limits farther from the center line, we
decrease the risk of a type I error—that is, the risk of a point
falling beyond the control limits, indicating an out‐of‐control
condition when no assignable cause is present.
• However, widening the control limits will also increase the risk of
a type II error—that is, the risk of a point falling between the
control limits when the process is really out of control.
• If we move the control limits closer to the center line, the
opposite effect is obtained: The risk of type I error is increased,
while the risk of type II error is decreased.
Choice of control limits
• In designing a control chart, we must specify both the
sample size and the frequency of sampling.
• In general, larger samples will make it easier to detect
small shifts in the process. This is demonstrated by the
operating‐characteristic curve.
Frequency of sampling
• We must also determine the frequency of sampling. The most
desirable situation from the point of view of detecting shifts
would be to take large samples very frequently; however, this
is usually not economically feasible. The general problem is
one of allocating sampling effort. That is, either we take small
samples at short intervals or larger samples at longer
intervals.
• Another way to evaluate the decisions regarding sample size
and sampling frequency is through the average run length
(ARL) of the control chart. Essentially, the ARL is the average
number of points that must be plotted before a point
indicates an out‐of‐control condition.
 Sensitizing rules for control charts
A control chart may indicate an out‐of‐control condition when
one or more points fall beyond the control limits or when the
plotted points exhibit some nonrandom pattern of behavior.
1. One or more points outside of the control limits.
2. Two of three consecutive points outside the two‐sigma
warning limits (zone A of the same side) but still inside
the control limits.
3. Four of five consecutive points beyond the one‐sigma
limits (Zones A or B of the same side).
4. A run of eight consecutive points on one side of the
center line.
5. Six points in a row steadily increasing or decreasing.
6. Fifteen points in a row in zone C (both above and below
the center line).
7. Fourteen points in a row alternating up and down.
8. Eight points in a row on both sides of the center line with
none in zone C.
9. An unusual or nonrandom pattern in the data.
10. One or more points near a warning or control limit.
Non-random patterns
Cyclic pattern
Possible causes: systematic
environmental changes such as
temperature, operator fatigue,
regular rotation of operators
and/or machines, or fluctuation
in voltage or pressure or some Mixture pattern
other variable in the production It is generated by two (or more)
equipment. Also because of overlapping distributions
maintenance schedules, or tool generating the process output.
wear resulting in excessive Sometimes mixtures result
variability. from “overcontrol. A mixture
pattern can also occur when
output product from several
Shift in process level sources (such as parallel
Possible causes: introduction machines) is fed into a common
of new workers; changes in stream.
methods, raw materials, or
machines; a change in the
inspection method or
standards; or a change in
either the skill, attentiveness,
or motivation of the
operators. Sometimes an
improvement in process
performance is noted
following introduction of a
control chart program, simply
Non-random patterns
Trend
Trends are usually due to a gradual
wearing out or deterioration of a
tool or some other critical process
component. In chemical processes,
they often occur because of
settling or separation of the
components of a mixture. They can
also result from human causes,
such as operator fatigue or the
presence of supervision. Finally,
trends can result from seasonal
influences, such as temperature.

Stratification
One potential cause of stratification
is incorrect calculation of control
limits. This pattern may also result
when the sampling process collects
one or more units from several
different underlying distributions
within each subgroup.
Phases of control chart application
• Phase I
• A set of process data is gathered and analyzed all at once in a retrospective
analysis, constructing trial control limits to determine if the process has been
in control over the period of time during which the data were collected, and
to see if reliable control limits can be established to monitor future
production.
• This is typically the first thing that is done when control charts are applied to
any process. Control charts in phase I primarily assist operating personnel in
bringing the process into a state of statistical control.
• Phase II
• Phase II begins after we have a “clean” set of process data gathered under
stable conditions and representative of in‐control process performance.
• In phase II, we use the control chart to monitor the process by comparing the
sample statistic for each successive sample as it is drawn from the process
to the control limits.
Phases of control chart application
• Thus, in Phase I, we are comparing a collection of, say, m points to a set of control
limits computed from those points.
• Typically, m = 20 or 25 subgroups are used in phase I.
• Control limits are calculated based on the m subgroups and the data plotted on the
control charts.
• Points that are outside the control limits are investigated, looking for potential
assignable causes.
• Points outside the control limits are then excluded and a new set of revised control
limits are calculated.
• Then new data are collected and compared to these revised limits.
• Sometimes this type of analysis will require several cycles in which the control chart is
employed, assignable causes are detected and corrected, revised control limits are
calculated, and the out‐of‐control action plan is updated and expanded.
• Eventually the process is stabilized, and a clean set of data that represents in‐control
process performance is obtained for use in phase II.
• Phase II focuses on process monitoring. Control limits are NOT recalculated.
Phases of control chart application
Phase I. Definition of control limits Phase II. Monitoring

• Take m subgroups of size n. • Set the sampling frequency

• Compute the control limits based based on process characteristics
on the collected samples. and monitoring needs.
• Verify that the process was • Collect samples at the
under control when the sample designated time intervals and
was taken. plot them on the control charts
• If the process was not under established during Phase I.
control, take appropriate • Analyze the control charts for
corrective actions (eliminate out- any signals indicating that the
of-control samples and process is out of control.
recalculate the limits). • If out-of-control signals are
detected, investigate potential
causes of variation, and
implement corrective actions to
bring the process back into
control.
Control charts for variables
• When dealing with a quality characteristic that is a
variable, it is usually necessary to monitor both the mean
value of the quality characteristic and its variability.
• Control of the process average or mean quality level is
usually done with the control chart for means, or the
control chart.
• Process variability can be monitored with either a control
chart for the standard deviation, called the S control
chart, or a control chart for the range, called an R control
chart. The R chart is more widely used.
 Control charts
• Suppose that m samples are available (m should be at least 20), each
containing n observations on the quality characteristic. Typically, n will be
small, often 4, 5, or 6.
• For each sample, the average and the range can be computed. Note that
• Then, the grand averages and are computed.
• The control limits for the control charts are given by:
chart chart
UCL UCL
CL CL
LCL LCL

where A2, D3 and D4 are constants that depend on the value of n.

• The chart monitors between-sample variability (variability in the process over
time), and the R chart measures within-sample variability (the instantaneous
process variability at a given time).
 Control charts
Example (Phase I):
• A hard-bake process is used in conjunction with photolithography in
semiconductor manufacturing. The specification limits on flow width
are 1.50 ± 0.50 microns.
• We wish to establish statistical control of the flow width of the resist
in this process using control charts.
• Twenty-five samples, each of size five wafers, have been taken when
we think the process is in control. The interval of time between
samples or subgroups is one hour. The flow width measurement data
(in microns) from these samples are shown in the Table in Excel.
• Compute the control limits of the charts and verify that the process
was under control when the samples were collected.
Control charts
Example (Phase II):
• Twenty additional samples of wafers from the hard-bake
process were collected after the control charts were
established.
• The data from these new samples are shown in the
Excel table.
• Monitor the process performance using the control
limits established in Phase I.
Operating-characteristic curve of
the chart
• The operating-characteristic (OC) curves
describe the ability of the control chart to
detect shifts in process quality.
• If the mean shifts from the in-control value,
say μ0, to another value μ1 = μ0 + kσ, the
probability of not detecting this shift on the
first subsequent sample or the β-risk is

• The value of β depends on the sample size

n.
• The expected number of samples taken
before the shift is detected is simply the
average run length, or
Operating-characteristic curve of
the R chart
• Similarly, for a shift on the process variability from to ,
the OC curve is:
 Control limits, specification limits
and natural variability limits
• Control limits: They are used to determine if a
process is under control. Control limits for , which
are estimated by .
• Natural limits (or natural tolerance limits).
They refer to the natural variability of the
process. Natural limits: . The process standard
deviation can be estimated as:

where d2 is a constant that depends on the

sample size.
• Specification limits. They are determined
externally. They may be set by management, the
manufacturing engineers, the customer, or by
product developers/designers. There is no
mathematical or statistical relationship between
the control limits and specification limits. A
quality characteristic outside the specifications
Estimating process capability
• Process capability quantifies how well a process can
produce output within specified limits. It assesses whether
a process is capable of consistently meeting customer
requirements or design specifications.
• Process capability measures:
• Fraction of non-conforming items: . It can be expressed as PPM.
• Process capability ratio (PCR) Cp.
• Process capability ratio adjusted for centering (PCRk) Cpk.
• Process performance ratios Pp and Ppk. Similar to Cp and Cpk but
calculated using long-term variation rather than short-term.
• Sigma level.
Process capability ratios
• Process capability ratio (PCR) Cp

• If  is unknown, it can be estimated through . Hence,

Process capability ratios
• Process capability ratio adjusted for centering (PCRk) Cpk

where

Where T is the target specification value. Cpk can also be

estimated by using replacing  with and Cp with .
Also, Cpk can be computed as
Process capability ratios
Process capability ratios
Sigma level
• It measures the number of standard deviations between the
mean performance and the closest specification limit.

• Its origin is the 6 process improvement methodology.

• 6 follows the DMAIC methodology for improving existing
processes or DMADV methodology for creating new products or
processes.
Measur Analyz Improv
Define Control
e e e

Measur Analyz
Define Design Verify
e e
Sigma level
• 6 aims to achieve a 3.4 defects per million of opportunities
when the process is centered 1.5 standard deviations away from
the target value. This means that 99.99966% of the products are

Probability that the product/process

within specifications.

complies with the specs.

100.0%

 Level Cp Defects
(PPM) 10.0%

3 1 66,810 1.0% 3 -sigma

4 - sigma
4 1.33 6,210 5 - sigma
0.1% 6 - sigma
5 1.67 233
6 2 3.4 0.0%

0.0%
1 10 100 1000 10000 1000001000000
Number of process stages or product components
Sigma level
• How bad is a 99.9% compliance level?
• At least 20,000 wrong prescriptions per year.
• More than 15,000 newborns dropped by doctors or nurses.
• No electricity, water or heat for 8.6 hours each year.
• No telephone service or TV transmission for nearly 10 minutes
each week.
• Two short (or long) landings at O’Hare each week.
• Automobiles brake failures? Defective airplanes? Parachute
failures?, etc.
Process capability
• The process capability measures make the following
assumptions:
1. The quality characteristic has a normal distribution.
2. The process is in statistical control.
Process capability and statistical
control
Is the process capable
of meeting the specs?

YES NO

SPC, DOE
YES
SPC DMAIC
Is the process
in control?
SPC, DOE
NO SPC DMAIC
 Control charts
• Control charts are preferred when either:
• the sample size n is moderately large—say, n > 10 or 12 (recall that the
range method for estimating σ loses statistical efficiency for moderate to
large samples), or
• the sample size n is variable.
• The control limits are given by
chart chart
UCL UCL
CL CL
LCL LCL

where A3, B3 and B4 are constants that depend on the value of n.

• The process standard deviation can be estimated by:
I – MR Control charts
There are many situations in which the sample size used for process
monitoring is n = 1; that is, the sample consists of an individual unit. Some
examples of these situations are as follows:
1. Automated inspection and measurement technology is used, and every
unit manufactured is analyzed so there is no basis for rational subgrouping.
2. Data become available relatively slowly, and it is inconvenient to allow
sample sizes of n > 1 to accumulate before analysis. The long interval
between observations will cause problems with rational subgrouping. This
occurs frequently in both manufacturing and nonmanufacturing situations.
3. Repeat measurements on the process differ only because of laboratory or
analysis error, as in many chemical processes.
4. Individual measurements are very common in many transactional,
business, and service processes because there is no basis for rational
subgrouping. Sometimes this happens because there are large time gaps
between service activities.
I – MR Control charts
• We use the moving range of two successive
observations as the basis of estimating the process
variability. The moving range is defined as

• The control limits are given by

I chart
chart
UCL
UCL
CL
CL
LCL
LCL
I – MR Control charts
• Example: The mortgage loan processing unit of a bank
monitors the costs of processing loan applications. The
quantity tracked is the average weekly processing
costs, obtained by dividing total weekly costs by the
number of loans processed during the week. The
processing costs for the most recent 20 weeks are
shown in the table in Excel. Set up individual and
moving range control charts for these data.
Control charts for attributes
• Attributes: non-conforming units (defectives) and non-
conformities (defects).
• Attributes charts are generally not as informative as variables
charts because there is typically more information in a
numerical measurement than in merely classifying a unit as
conforming or nonconforming.
• However, attributes charts do have important applications.
They are particularly useful in service industries and in
nonmanufacturing or transactional business process and
quality improvement efforts because so many of the quality
characteristics found in these environments are not easily
measured on a numerical scale.
p chart
• Control chart for fraction nonconforming.
• Select m preliminary samples, each of size n. As a general rule,
m should be at least 20 or 25. Then if there are Di nonconforming
units in sample i, we compute the fraction nonconforming in the
ith sample as

• Hence, the statistic that estimates the unknown population

chart
fraction of nonconforming units p is
UCL
CL
• The control limits of the p chart are given by: LCL
p chart
• Example: Frozen orange juice concentrate is packed in
6‐oz cardboard cans. These cans are formed on a
machine by spinning them from cardboard stock and
attaching a metal bottom panel. By inspection of a can,
we may determine whether, when filled, it could
possibly leak either on the side seam or around the
bottom joint. Such a nonconforming can has an
improper seal on either the side seam or the bottom
panel. Set up a control chart to improve the fraction of
nonconforming cans produced by this machine.
np chart
• It is also possible to base a control chart on the number
nonconforming rather than the fraction nonconforming.
• The control limits of the np chart are given by:
chart
UCL
CL
LCL
Control charts for noncomformities
(defects)
• A defective unit might have multiple defects.
• It is possible to develop control charts for either the
total number of nonconformities in a unit or the average
number of nonconformities per unit.
• These control charts usually assume that the occurrence
of nonconformities in samples of constant size is well
modeled by the Poisson distribution.
• The inspection unit must be the same for each sample.
c chart
• Consider the occurrence of nonconformities in an inspection unit of product. In
most cases, the inspection unit will be a single unit of product, although this is not
necessarily always so.
• The inspection unit is simply an entity for which it is convenient to keep records. It
could be a group of 5 units of product, 10 units of product, and so on.
• The c chart controls the total number of nonconformities in one inspection unit.
• Select m preliminary samples, each sample consists of one inspection unit (which
can comprise multiple units of product). ci defects are found in the ith sample.
Hence, is the average number of defects in one inspection unit.
• The control limits are given by: chart
UCL
CL
LCL
c chart
• Example: The table in excel presents the number of
nonconformities observed in 26 successive samples of
100 printed circuit boards. Note that, for reasons of
convenience, the inspection unit is defined as 100
boards. Set up a c chart for these data.
u chart
• The inspection unit is chosen for operational or data‐collection
simplicity. However, there is no reason why the sample size must
be restricted to one inspection unit.
• The u chart controls the average number of nonconformities per
inspection unit.
• Select m preliminary samples, each sample consists of n inspection
units. xi defects are found in the ith sample. Hence, is the average
number of defects in one inspection unit in the ith sample.
chart
• The control limits are given by: UCL
CL
LCL
Choice between attributes and
variable control charts
• Attributes control charts:
• Several quality characteristics can be considered jointly
• There is an obvious simplicity associated with the attributes chart.
• Furthermore, expensive and time‐consuming measurements may sometimes be
avoided by attributes inspection.
• Variables control charts
• Provide much more useful information about process performance than do attributes
control charts.
• When points plot out of control on variables control charts, usually much more
information is provided relative to the potential cause of that out‐of‐control signal.
• They often provide an indication of impending trouble and allow operating personnel
to take corrective action before any defectives are actually produced.