Quality Assurance

Dr. Janakarajan Ramkumar

Professor
Department of Mechanical & Design Program
IIT Kanpur, India.
 Contents
 Introduction
 Process Capability
 Process Capability Analysis Using a Control Chart
 Process Capability Analysis Using Design of Experiments
 Engineering Process Control (EPC) and SPC
 Process Monitoring and Process Regulation
 Process Control by Feedback Adjustment
 Combining SPC and EPC
Introduction
• Statistical techniques can be helpful throughout the product
cycle, including development activities prior to manufacturing:

• in quantifying process variability,

• in analysing this variability relative to product requirements
or specifications, and
• in assisting development and manufacturing in eliminating or
greatly reducing this variability.

• This general activity is called process capability analysis.

Process Capability
• Process capability refers to the uniformity of the process.
• The variability of critical-to-quality characteristics in the process is
a measure of the uniformity of output.

There are two ways to think of this variability:

1. The natural or inherent variability in a critical-to-quality
characteristic at a specified time—that is, “instantaneous”
variability
2. The variability in a critical-to-quality characteristic over time
Process Capability Ratios
Use and Interpretation of Cp

• where USL and LSL are the upper and lower specification limits,
respectively.
Process Capability Ratios
Process Capability Ratio for an Off-Centre Process

• The process capability ratio Cp does not take into account

where the process mean is located relative to the
specifications.
• Cp simply measures the spread of the specifications relative to
the Six Sigma spread in the process.

• This situation may be more accurately reflected by defining a

new process capability ratio (PCR)—Cpk—that takes process
centering into account.
Process Capability Ratios
Normality and the Process Capability Ratio

• An important assumption underlying our discussion of process

capability and the ratios Cp and Cpk is that their usual
interpretation is based on a normal distribution of process
output.

• If the underlying distribution is non-normal, then, the

statements about expected process fallout attributed to a
particular value of Cp or Cpk may be in error.

• One approach to dealing with this situation is to transform the

data so that in the new, transformed metric the data have a
normal distribution appearance.
Process Capability Ratios
Normality and the Process Capability Ratio

• Other approaches have been considered in dealing with non-

normal data.

• There have been various attempts to extend the definitions of

the standard capability indices to the case of non-normal
distributions.

• Luceño (1996) introduced the index Cpc , defined as

• where the process target value

Process Capability Analysis Using a Control Chart
• Histograms, probability plots, and process capability ratios
summarize the performance of the process.
• They do not necessarily display the potential capability of the
process because they do not:
• address the issue of statistical control, or
• show systematic patterns in process output that, if
eliminated, would reduce the variability in the quality
characteristic.
Process Capability Analysis Using a Control Chart

• Control charts are very effective in this regard.

• The control chart should be regarded as the primary
technique of process capability analysis.
• Both attributes and variables control charts can be used in
process capability analysis.
• The and R charts should be used whenever possible, because
of the greater power and better information they provide
relative to attributes charts.
• However, both p charts and c (or u) charts are useful in
analysing process capability.
Process Capability Analysis Using DoE

• A designed experiment is a systematic approach to varying the

input controllable variables in the process and analysing the
effects of these process variables on the output.

• Designed experiments are also useful in discovering:

• which set of process variables is influential on the output,
and
• at what levels these variables should be held to optimize
process performance.

• One of the major uses of designed experiments is in isolating and

estimating the sources of variability in a process.
Engineering Process Control (EPC) and SPC
• There are two statistically based approaches for addressing this
problem:

• The first of these is statistical process monitoring by control

charts, or statistical process control (SPC).
• The focus of SPC is on identifying assignable causes so that
they can be removed, thereby leading to permanent process
improvement or reduction in variability.

• The second approach is based on adjusting the process using

information about its current level or deviation from a desired
target.
• This approach is often called feedback adjustment, and it is a
form of Engineering Process Control or EPC.

• Feedback adjustment regulates the process to account for sources

of variability that cannot be removed by the SPC approach.
Engineering Process Control (EPC) and SPC
• Engineering Process Control (EPC) is a process compensation or
regulation schemes are widely known as stochastic control, or
feedback or feedforward control, depending on the nature of the
adjustments.

• This approach is based on process compensation and regulation, in

which some manipulatable process variable is adjusted with the
objective of keeping the process output on target (or equivalently,
minimizing the variability of the output around this target).

• SPC has had a long history of successful use in discrete parts

manufacturing.
• EPC is used in continuous processes, such as those found in the
chemical and process industries to reduce variability.
Process Control by Feedback Adjustment
A Simple Adjustment Scheme: Integral Control
• In this we consider a simple situation involving a process in
which feedback adjustment is appropriate and highly
effective.
• The process output characteristic of interest at time period t
is yt, and we wish to keep yt as close as possible to a target T.
This process has a manipulatable
• variable x, and a change in x will produce all of its effect on y
within one period—that is,

• where g is a constant usually called the process gain. The

gain is like a regression coefficient, in that it relates the
magnitude of a change in xt to a change in yt.
• Now, if no adjustment is made, the process drifts away from
the target according to

• where Nt + 1 is a disturbance.
Process Control by Feedback Adjustment
The Adjustment Chart

• When EPC or feedback adjustment is implemented in this

manner, it is often called automatic process control (APC).
• In many processes, feedback adjustments can be made
manually.
• Operating personnel routinely observe the current output
deviation from target, compute the amount of adjustment to
apply, and then bring xt in the following equation to its new
set point.
 Combining SPC and EPC
• There is considerable confusion about process adjustment versus
process monitoring.
• Process adjustment or regulation has an important role in reduction of
variability.
• There are many processes where some type of feedback-control
scheme would be preferable to a control chart.
• In processes where feedback control is used there may be substantial
improvement if control charts are also used for statistical process
monitoring (as opposed to control; the control actions are based on the
engineering scheme).
 Combining SPC and EPC

• The control chart should be applied either

• to the control error (the difference between the controlled
variable and the target) or
• to the sequence of adjustments to the manipulated
variable. Combinations of these two basic approaches are
also possible.

• Points that lie outside the control limits on these charts would
identify periods during which the control errors are large or
during which large changes to the manipulated variable are
being made.

• These periods would likely be good opportunities to search for

assignable causes.
Task for students
Thanks