See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/286440390

Measuring Process Capability Indices

Conference Paper · June 2006

CITATIONS READS

7 1,819

3 authors:

Kamran. Rezaie Ostadi Bakhtiar

University of Tehran Tarbiat Modares University
39 PUBLICATIONS 896 CITATIONS 65 PUBLICATIONS 588 CITATIONS

SEE PROFILE SEE PROFILE

Mohammadreza Taghizadeh-Yazdi
University of Tehran
121 PUBLICATIONS 605 CITATIONS

SEE PROFILE

All content following this page was uploaded by Mohammadreza Taghizadeh-Yazdi on 10 December 2015.

The user has requested enhancement of the downloaded file.

 Measuring Process Capability Indices

K. Rezaie, B. Ostadi, M.R. Taghizadeh

Dep. of Industrial Engineering, Faculty of Engineering, Univ. of Tehran, Tehran, Iran.

P.O. Box: 11365/4563, Tehran, Iran, +98 21 88021067
krezaie@ut.ac.ir

Abstract

Process capability indices, Cp and Cpk have been proposed in the manufacturing industry and the service
industry providing numerical measures on whether a process is capable of reproducing items within the
specification limits preset in the factory. In recent years an increasing number of organizations use
process capability studies on a regular basis. Contemporaneous with the increasing number of
organizations using process capability studies, warnings have been launched that imprudent use of
numerical measures of capability, the so-called process capability indices, might lead the user to make
erroneous decisions. In this paper, the process capability indices are presented and process capability
studies be presented from a practical point of view.

KEY WORDS : Process Capability Index, measurement of process capability, parts per million,
Criticisms

1 Introduction

Cp is defined as the ratio of specification width over the process spread. The specification width
represents customer and/or product requirements. The process spread represents the process variations.
When the process variation is large (more variation), the Cp value is small, indicating a low process
capability. The process capability index Cpk is used to provide an indication of the variability associated
with a process and how a process has conformed to its specifications. The index is usually used to relate
the "natural tolerance" (3σ), to the specification limits. Different from Cp, Cpk describes how well the
process fits within the specification limits, taking into account the location of the process mean.

The capability of a process is the quantification of the current and the expected future common cause
variation. The quantification of process location and variance is essential in order to evaluate the potential
quality of products manufactured. A theoretical framework has been established for how to assess the
capability of processes. These analyses are often called process capability studies or process capability
analyses. The objective of using process capability studies is first of all to receive information about the
process, information that can form a base for improvement efforts leading to a more capable process.

During the last couple of years the method process capability studies and the numerical measures of
capability used, the so-called process capability indices, have received a somewhat torn reputation.
Practitioners have experienced that, sometimes, the values of process capability indices they receive
indicate that a process they know as capable might be incapable, and vice versa. The reason for this is that
estimates of process capability indices are often treated as exact measures of capability of the process and
not as the estimates they actually are. Some researchers have also reported on the shortcomings of process
capability indices; see, for instance, (Gunter, 1989; Dovich, 1991a; Dovich, 1991b; Pignatiello and
Ramberg, 1993). As indicated, the criticism has been focused on the specific measures of capability, the
process capability indices, and not primarily on the method process capability studies, as such. However,
the shortcomings of process capability indices are not as severe as the misuse of them, see (Deleryd, 1996
and 1999) or in other words, if process capability indices are used properly and with care, they provide
valuable information about the capability of a process. The information received is most useful when
improving the performance of processes, leading to lower production costs or more satisfied customers, or
both.

In this paper, a number of process capability indices are presented. Throughout the presentation, it is
assumed that the process output is approximately normally distributed and in a state of statistical control.
Also, process capability studies are presented from a practical point of view.

2 What is Process Capability?

(a) Process capability is the long-term performance level of the process after it has been brought
under statistical control. In other words, process capability is the range over which the natural
variation of the process occurs as determined by the system of common causes.

(b) Process capability is also the ability of the combination of people, machine, methods, material,
and measurements to produce a product that will consistently meet the design requirements or
customer expectation.

3 What is a Process Capability Study?

Process capability study is a scientific and a systematic procedure that uses control charts to detect and
eliminate the unnatural causes of variation until a state of statistical control is reached. When the study is
completed, you will identify the natural variability of the process.

4 Why Should I Know the Capability of my Processes?

(a) Process capability measurements allow us to summarize process capability in terms of

meaningful percentages and metrics.

(b) To predict the extent to which the process will be able to hold tolerance or customer
requirements. Based on the law of probability, you can compute how often the process will meet
the specification or the expectation of your customer.

(c) You may learn that bringing your process under statistical control requires fundamental changes –
even redesigning and implementing a new process that eliminates the sources of variability now
at work.

(d) It helps you choose from among competing processes, the most appropriate one for meeting
customers' expectation.

(e) Knowing the capability of your processes, you can specify better the quality performance
requirements for new machines, parts and processes.

5 Process Capability Indices

 (a) Cp, Cpl, Cpu, and Cpk are the four most common and timed tested measures of process
capability.

(b) Process capability indices measure the degree to which your process produces output that
meets the customer's specification.

(c) Process capability indices can be used effectively to summarize process capability
information in a convenient unitless system

Cp and Cpk are quantitative expressions that personify the variability of your process (its natural
limits) relative to its specification limits (customer requirements). Following are the graphical
details (Fig. 1) and equations quantifying process capability (Table 1):

Figure 1: The graphical details

Table 1: Equations of process capability

6 Process Capability and Defect Rate

Using process capability indices it is easy to forget how much of product is falling beyond specification.
The conversion curve presented here can be a useful tool for interpreting Cpk with its corresponding defect
levels. The defect levels or parts per million non-conforming were computed for different Cpk values
using the Z scores and the percentage area under the standard normal curve using normal deviate tables.
The Table 2 presents the non-conforming parts per million (ppm) for a process corresponding to Cpk
values if the process mean were at target.

Table 2: The non-conforming parts per million (ppm)

The Cpk conversion curve for process with mean at target is shown in the Fig. 2. A process with Cpk of 2.0
(+/-6 sigma capability), i.e., the process mean is 6 sigma away from the nearest specification can be
expected to have no more than 0.002 nonconforming parts per million. This process is so good that even
if the process mean shifts by as much as +/- 1.5 sigma the process will produce no more than 3.4 non-
conforming parts per million.

Figure 2: The Cpk conversion curve for process

7 Case study: Process Capability Indices

An example provided by Kane (1986) and extended by Chan et al. (1988) will be considered, where the
radial lengths of machined holes in transmission differentials were measured (Table 3). The radial length
of a machine hole is the distance between the center of the hole and the centerline of the transmission
differential. The measurements were made using a coordinate measuring machine. The upper
specification limit was determined to be 20 units and the lower −20 units, with a target value of zero for
the process mean. The next table provides a summary of the results from three stages of the process. In
the first stage, the process capability was poor, while in the second stage, it was much worse. In the third
stage, there was a noticeable improvement in the process capability. In the third stage, although the value
=1.23 renders the process capable, since =0:93 and =0:91, it is apparent that if the proximity to the target
value is important, then the process should not be considered capable. In this case, the value of is
deceiving, and centering and/or reducing its variability is required. This case illustrates the character of
estimates of indices that take into account both the process variance and proximity to the target value and
demonstrates the significance of their use.

Stage n X S ĈP ĈPm

1 201 4.7 8.7 0.77 0.59
2 96 10.4 21.1 0.32 0.15
3 316 5.0 5.4 0.23 0.93
Table 3: Date for the example (radial length (× 10 3 in))

8 Criticisms of process capability indices

I will present some criticisms which have arisen from the implementation of process capability indices.
However, it should be pointed out that problems are mainly due to insufficient understanding of statistical
principles on the part of the implementers. Throughout this discussion of indices, it has been assumed that
the process output is in a state of statistical control. One problem arises because people who use these
indices tend to want to assess the capability of a process without having established statistical control.
Since capability indices quantify common cause variation as well as predict future process capability, the
presence of special causes of variation distorts the interpretation of capability indices and renders
prediction unsuccessful. It has also been assumed throughout this discussion that the process output is
approximately normally distributed. Another problem is due to the fact that a given process output may
not be normal, and Kane (1986) states that capability indices are somewhat sensitive to departures from
normality. Kane (1986) suggests that data transformations be used to attain approximate normality in such
cases. Finally, since not all employees of a given plant are knowledgeable about mathematical formulas, it
can be difficult to compute values of indices without special training or access to automated procedures.

9 Conclusions

In the real world, very few processes completely satisfy all the conditions and assumptions required for
estimating Cpk. Also, statistical debates in research communities are still raging on the strengths and
weaknesses of various capability and performance indices. Many new complicated capability indices have
also been invented and cited in literature. However, the key to effectual use of process capability
measures continues to be the level of user understanding of what these measures really represent. Finally,
in order to achieve continuous improvement, one must always attempt to refine the "Voice of the Process"
to match and then to surpass the "Expectations of the Customer".
 Process capability indices, Cp and Cpk, are useful, so long as the fundamental underlying assumptions,
such as normal distribution, stable process and variable data, are known. If two processes are identical
except one with higher Cpk than another, then the process yield with higher Cpk will be higher than the
process with lower Cpk. Since Cp does not take the process mean into account and reflect the non-
conformance rejects, the conclusion does not apply to Cp. However Cpk cannot replace yield, unless all
other conditions and processes are the same.

When the Cp and Cpk indices are examined jointly, some critical information about the process capability
is revealed. Since Cpk is indirectly related to the percentage of non-conforming products, it may be used as
an estimation of the process capability to produce products that conform to specifications in terms of the
specific process characteristics. Cp, when shown together with Cpk, gives a quick estimate of how far the
actual process is from its target, and thus, how much work is needed to bring the process to its potential.

References

Deleryd, M. (1996). Process capability studies in theory and practice. Licentiate Thesis, Division of Quality
Technology & Statistics, Lulea University of Technology, Sweden.
Deleryd, M. (1999). A pragmatic view on process capability studies. Int. J. Production Economics, 58, 319-330.
Dovich, R.A. (1991a). In: ASQC Statistical Division Newsletter, 5.
Dovich, R.A. (1991b). Statistical Terrorists II - it's Not Safe Yet, Cpk Is Out There. MS, Ingersoll Cutting Tools Co.,
Rockford, IL.
Gunter, B. (1989). The use and abuse of Cpk, Parts 1-4, Quality Progress, Part 1: 22(1) 72-73, Part 2: 22(3) 108-109,
Part 3: 22(5) 79-80 and Part 4: 22(7) 86-87.
L.K. Chan, S.W. Cheng, F.A. Spiring, (1988). A new measure of process capability: Cpm. J. Qual. Technol., 20, 162–
175.
Pignatiello, J.J., Ramberg, J.S. (1993). Process capability indices: Just say no!. Proceedings of the 47th ASQC
Annual Quality Congress, Boston, 1993, pp. 92-104.
Ramakrishnan, B., Sandborn, P. and Pecht, M., (2001). Process capability indices and product reliability,
Microelectronics Reliability. 41, 2067-2070.
V.E. Kane, (1986). Process capability indices. J. Qual. Technol., 18, 41–52.

View publication stats