Statistical Process Control (SPC)

What is SPC?

◼ Statistical Process Control (SPC) is a procedure in

which DATA IS COLLECTED, ORGANIZED,
ANALYZED AND INTERPRETED so that the
process can be maintained at its present level of
quality or improved to higher level of quality
 Collection of Data – Small samples
 Organization of data – tables, charts or graphs
 Analysis of data – Average and spread
 Interpretation of data – to see if process in statistical
control
PREVENTION VERSUS DETECTION

◼ In the past, manufacturing often depended on production to

make the product and on quality control to inspect the
finished product to identify the units not meeting the
specification. In this context, the product is checked and
rechecked in efforts to catch errors. This involves the
strategy of DETECTION, which is wasteful, because it allows
time and material to be invested in products and services
that are not always usable.
◼ It is much more effective to avoid waste by not producing
unusable output in the first place – a strategy of
PREVENTION.
◼ A prevention strategy sound sensible – even obvious – to
most people. It is easily captured in such slogans as “RIGHT
FIRST TIME”.
Process Control System

◼ A process control system can be described as

a feedback system.
VOICE OF THE PROCESS STSTISTICAL

METHODS

PEOPLE
EQUIPMENT THE WAY WE PRODUCT /
SERVICES CUSTOMERS
MATERIAL WORK / BLENDING
METHOD
ENVIRONMENT
OF RESOURCES
IDENTIFYING
CHANGING NEEDS
AND EXPECTATIONS

INPUT PROCESS / OUTPUT

SYSTEM

VOICE OF CUSTOMER
Elements of Process Control

◼ The Process – The process means the whole

combination of suppliers, producers, people,
equipment, input material, methods and
environment that work together to produce
output and the customers who use the
output.
Elements of Process Control
◼ Information About Performance – Much information about the
actual performance of the process can be learnt by studying the
process output. The most helpful information about the
performance of a process comes, however, from understanding
the process itself, and its internal variability. Process
characteristics (temperature, cycle time, feed rate etc.) should be
the ultimate focus of our efforts. We need to determine target
values for those characteristics which result in the most productive
operation of the process, and then monitor how near or far from
those target values we are. If this information is gathered and
interpreted correctly, it can show whether the process is acting in
usual or un-usual manner. Proper action can then be taken, if
needed, to control the process or the just produced output. When
action is needed it must be timely and appropriate or the
information gathering efforts are wasted.
Elements of Process Control
◼ Action on the Process – Action on the process is
frequently most economical when taken to
prevent the important characteristics (process or
output) from varying too far from their target
values. This maintains the stability and the
variation of the process output within acceptable
limits. Such action might consist of changes in the
operations (eg. Operator training, changes to the
incoming material etc.) or the more basic
elements of the process itself (eg equipment that
may need calibration).
Elements of Process Control

◼ Action on the Output –Action on the output is

frequently the least economical when it is
restricted to detecting and correcting out-of-
specification product without addressing the
process problem.
Concept of Variation
◼ No two products or
characteristics are exactly alike,
because any process contains
many sources of variability. The
differences amongst the
products may be large or
immeasurably small, but they
are always present.
◼ While individual measured
values may all be different, as a
group they tend to form a
pattern that can be described
as a distribution.
Concept of Variation
◼ PIECES VARY FROM EACH
OTHER BUT THEY FOR A
PATTERN THAT IS STABLE
AND CAN BE DESCRIBED
AS DISTRIBUTION
◼ These distributions can be
characterized by:
 Location (typical value)
 Spread (span of values from
smallest to largest)
 Shape (the pattern of
variation – whether it is
symmetrical, skewed etc.)
Concept of Variation

◼ Some sources of variation in the process

cause, short term “piece-to-piece” variation.
Other sources of variation tend to cause
changes in the output only over a longer
period of time, either gradually as with tool
wear or irregularly as with environmental
changes such as power surge.
Concept of Variation

◼ From the standpoint of minimum

requirements, the issue of variation may be
restricted to conformance or non-
conformance to specifications. However, to
manage any process and reduce variation, the
variation must be traced back to its sources.
The first step is to make distinction between
common and special causes of variation.
Concept of Variation
◼ Common causes refer
to the many sources
of variation within a
process that has a
stable and repeatable
distribution over a
period. Such a process
in a
is called “
state of
statistical
control”.
Concept of Variation
◼ Special causes (often called Assignable causes) refer to any factor
causing variations that are not always acting on the process.
◼ That is, when they occur, they make the overall process
distribution change.
◼ Unless all the special causes of variation are identified and acted
upon, they will continue to affect the process output in an
unpredictable manner.
◼ If special causes of variation are present, the process output is
NOT stable over a period.
Setting up Control Chart
◼ Select the size, frequency and number of subgroups
 Subgroup Size: For an initial study, the subgroup could
typically consist of 4-5 consecutively produced pieces,
representing only a single tool, head die cavity etc.
 Subgroup frequency: The goal is to detect changes in the
process over time. Subgroups should be collected often
enough and at appropriate times, that they can reflect the
potential opportunities for change.
 Number of subgroups: From process standpoint, enough
subgroups should be gathered to assure that the major
sources of variation (Special cause) have had an opportunity
to appear. Generally 25 or more subgroups give a good test
for stability, and if stable, good estimate of process location
and spread.
Setting up Control Chart
◼ Set up Control chart and
record raw data
 X-bar and R chart are
normally drawn with the X-
bar chart above the R chart
and a data block. The
values of X-bar and R will
be vertical scales, while the
sequence of subgroups
through time will be the
horizontal scale.
Calculate the Average (X) and the Range
(R) for each subgroup:

◼ The characteristics to be plotted are the

sample average (X) and the sample range (R)
for each subgroup, collectively, these reflect
the overall process average and its variability,
respectively.

Calculate the X-bar and the R for each subgroup. Calculate X- Double bar and R bar
Plot the Averages and the Ranges on the
Control Charts
CALCULATE CONTROL LIMITS
◼ Control limits for the range chart are
developed first, then those for the chart for
averages.
◼ Control limits are calculated to show the
extent by which the subgroup averages and
ranges would vary if only common causes of
variation were present. They are based on the
subgroup sample size and the amount of
within subgroup variability reflected in the
ranges. Calculate the upper and lower control
limits for ranges and averages:
Plot Control Limits
Interprete for Process Control
◼ The objective of control chart analysis is to identify
any evidence that process variability or the process
average are NOT operating at a constant level – that
one or both are out of statistical control – and to
take appropriate action.
◼ Since the ability to interpret either the subgroup
range or subgroup averages depend on estimates of
piece-to-piece variability, the R chart is analyzed
first. The data points are compared with the control
limits, for points out of control or for unusual
patterns or trends.
22
Interprete for Process Control
◼ Points beyond control limits - The presence of one or more points
beyond either control limit is primary evidence of non control at that
point.

◼ A point above the upper control limit is generally a sign of one or more
of the following;
◼ • Control limit or a the point miscalculated or mis-plotted;
◼ • Piece-to-piece variability or the spread of the distribution has
increased (worsened)
◼ • The measurement system has changed (inspector or the gage)

23
Interprete for Process Control

◼ Runs – Each of the following are the signs that

process shift or trend has begun;
◼ • 7 points in a row on one side of the
average
◼ • 7 points in a row that are constantly
increasing or decreasing

24
Process Capability & Process
Performance
◼ Indices of process ◼ Definitions of process terms
variation only, relative ◼ Inherent Process Variation -
that portion of the process
to the specifications- Cp
variation due to common
and Pp causes only.
◼ Indices of process ◼ Process Capability - The
variation and centering range of process's inherent
combined, relative to variation, for statistically
the specifications- CPU, stable processes only,
where s is usually
CPL, Cpk.
estimated by

25
Constants

26
Definition of Process Measures
◼ Cp -
• This is the capability
index defined as the
tolerance width divided
by the process
capability, irrespective
of process centering
• The larger the index,
the less likely it is that
any item will be outside
the specs.

27
Evaluating Cp and Cpk

0.714 The Cpk index is calculated as

USL = 0.900
LSL = 0.500
CPU =

CPL =

28
 Exercise
Food served at a restaurant should be between 39°C and 49°C
Given,
USL (Upper Specification Limit) =49°C
LSL (Lower Specification Limit) =39°C
Standard Deviation =2°C
Mean = 40
To Find,
Process Capability & Process Capability Index

29
Estimating proportion
Nonconforming
◼ Calculate ZUSL and ZLSL

2.5 2.9
6 5

30
Estimating proportion
Nonconforming
2.5 0.52%
6
2.9 0.16%
5
Conclusion
@0.68% production
is out of specification

31
Individual X Moving Range Chart

In some cases, it is necessary for process

control to be based on individual readings,
rather than subgroups.
This would typically occur when
measurements are expensive ( example
destructive test) or when The output at any
point at a given time is homogeneous (
example pH of a given solution)

32
Individual X Moving Range Chart

33
 Types of Attribute Chart

Defects data is the number Rejects data where the entire item
of non-conformities within is judged to conform to product
an item. There is no limit to specifications or not. The count
the number of possible for each item is limited to 1or 0.
defects. Defects charts Rejects charts count the number of
count the number of defects rejects in a subgroup.
in the inspection unit. 34
p Chart for Units Nonconforming

◼ Each component, part or item being checked

is recorded as either conforming or
nonconforming ( even if an item has several
specific non conformities, it is only tallied
once as non conforming item).
◼ The number of non conforming items are
expressed as a decimal fraction of the
subgroup size.
35
p Chart for Units Nonconforming

36
p Chart for Units Nonconforming

37
 np Chart for Number
Nonconforming
• The np Chart measures the number of
nonconforming items in an inspection lot.
• It is identical to the p chart, except that the
actual number of non conforming items, rather
than their proportion is recorded.
• Both p and np Chart are appropriate for the
same basic situation, with the choice going to np
Chart if (a) the actual number of nonconformities
is more meaningful or simpler to report than the
proportion, and (b) the sample size remains
38
np Chart for Number
Nonconforming

39
np Chart for Number
Nonconforming

40