14th International Research/Expert Conference
”Trends in the Development of Machinery and Associated Technology”
TMT 2010, Mediterranean Cruise, 11-18 September 2010
ROLE OF GAGE R&R IN ESTIMATION OF PROCESS CAPABILITY
Biserka Runje, Gorana Baršić, Vesna Alar
Faculty of Mechanical Engineering and Naval Architecture
Ivana Lučića 5, 10000 Zagreb
Croatia
ABSTRACT
Capable process is a process that is able to produce items within the specification limits. The ability of
a process to meet specifications can be expressed by using process capability indices. In order to have
an accurate estimation of process capability quality management system is required. Gage
repeatability and reproducibility analysis (gage R&R) addresses the issue of measurement system
precision. If measurement system is not repeatable or reproducible relatively to the variability
between items, then that measurement system is not sufficiently precise to be used in product
capability analyses. In the ideal case, all variability’s in measurements are results of item variation,
and only a negligible proportion of the variability’s will be due to gage R&R. In this paper an analysis
of the influence of quality measurement system on process capability has been carried out.
Keywords: process capability, process capability indices, gage R&R
1. ESTIMATION OF PROCESS CAPABILITY
Estimation of process capability together with statistical control and design of experiments are
statistical methods that have been used for years in an attempt to reduce variability of production
process and their final products. Process capability refers to the normal behavior of a process not
affected by any significant factors and it is customary expressed as a percentage of process under
given tolerances. Fundamental requirement of process capability is T ≥ 6σ . Process is capable if
requirement range T is greater or equal to process range 6 σ . Process range means area within ± 3
standard deviations σ in relation to process mean , which represents 99,73% of surface below the
normal distribution curve used to approximate the process. Process capability is estimated by
calculating, the so called process capability indices. Calculation and proper interpretation of process
capability indices is based on following suppositions:
data distribution can be approximated by the normal distribution
reliable estimation of process capability can be made only based on process monitoring using
appropriate control chart and after bringing the process in the condition of statistical control (status
under control).
It makes sense to estimate process capability only when special causes affecting process variations are
removed and medium process brought to the environment of target value.
1.1. Process capability indices
By taking into consideration time when process is taking place, in accordance to interpretation of the
Ford company, process capability indices may be estimated in a longer time period, as Preliminary
Process Capability and in a shorter time period as Short-Term Capability.
Process capability indices in a longer time period are calculated after process took place over some
period of time, during which all possible effects of process variations could appear. The most common
indices used are those for calculating potential process capability C p and demonstrated excellence
189
index C PK . C p index describes tolerance field range in reference to actual data dispersion, while
C PK index defines the process position in reference to requirement limits. Process capability indices
are provided in the expressions (1) i (2).
C p = ( USL − LSL ) / 6σ = T / 6σ (1)
C pK = min(( USL − x ) / 3σ ;( x − LSL ) / 3σ ) (2)
where::
USL - upper specification limit
LSL - lower specification limit
T - tolerance area
- arithmetic mean (central line of the control chart)
6σ - observed process range
In the expressions (1) and (2) standard deviation has been estimated on the basis of data from control
chart. Various control charts are used for detection of variations in the process and determining
amount of process standard deviation.
Preliminary estimation of process capability is conducted in the beginning of process or after short
process monitoring. In the name of indices the term performance is used instead of capability.
Therefore indices are labeled as Pp i Ppk. They are calculated in the same manner as Cp i Cpk, with the
exception that standard deviation, the so called overall standard deviation, is estimated from all data
based on expression 3.
n
∑ (x i − x)2
(3)
σ =s= i =1
n −1
2. ANALYSIS OF MEASUREMENT SYSTEM IN PRODUCTION ENVIRONMENT
In order to estimate quality of the measurement system it is necessary to identify and quantify sources
of variability, define stability and determine measurement system capability. Measurement system
needs to be analyzed upon receiving new measuring equipment, when comparing measuring
characteristics of various measuring equipment, when establishing system errors, when comparing
measurement characteristics before and after repair of measuring equipment, and in identifying
components for calculating measurement process variations and estimating acceptability for
production process control. In the event that measurement system variation is significant in
comparison to established variation of the item that is measured in a production process, system may
not provide valid information on process control. For this reason, prior to establishing process stability
and capability, it is necessary to analyze measuring system and determine whether measuring system
will be able to consistently, accurately, and precisely differentiate between parts of the process.
2.1. Estimation of measurement system capability
Requirement for estimating quality of measurement systems stems from a very simple fact that
measurements are in no way perfect. Variations in the measurement system result from random and
systematic effects. Main sources of measurement system variability are the item that is measured,
equipment, operator and environment. Significance of elements in the measurement system is
expressed by the amount of dispersion of measuring results obtained in defined measurement
conditions. Impacts of individual elements of measurement system can be classified in three main
categories:
Repeatability – EV
Repeatability is defined as the impact of measuring equipment in the measurement system variation.
Repeatability represents dispersion of measurement results obtained by one operator during multiple
measurements of identical characteristics on the same parts (samples), while using the same
instrument.
190
Reproducibility - AV
Reproducibility is defined as the impact of operators conducting in the measurement system variation.
Reproducibility represents dispersion of measurement results obtained by several operators during
multiple measurements of identical characteristics on the same parts (samples), while using the same
or different instrument.
Part variation – PV
Part variation is defined as the impact of parts (items) in the total variation of measurement system TV.
Measurement system variation R&R
Measurement system variation depends on the total dispersion of measurement results due to mutual
effect of repeatability and reproducibility R&R. Calculation of the measurement system variation R&R
is provided in the expression 4.
R & R = EV 2 + AV 2 (4)
Total variation TV
Total variability TV (expression 5) depends on the variation of measurement system R&R and parts
variation PV.
TV = (R & R ) + PV 2
2
(5)
Measurement system capability
Measurement system capability represents share of measurement system variability R&R expressed as
percentage of total variation TV or tolerance field T, i.e. share of measurement system variance in the
total variance. Expressions for calculating measurement system capability are as follows:
Measurement system capability = R & R / TV ⋅ 100% (6)
Measurement system capability = R & R / T ⋅ 100% (7)
Contribution = σ 2R&R / σTV
2
⋅100% (8)
Criteria for assessing quality of measurement system R&R in the tolerance field T or total variation TV
are provided in table 1, and criteria for assessing quality of measurement system R&R for contribution
percentage are provided in the table 2.
Table 1. Criteria for assessing quality of gage Table 2. Criteria for assessing quality of gage
R&R in the tolerance field T or total variation TV. R&R for contribution percentage.
% T, %TV Gage R&R is Contribution % Gage R&R is
< 10 Acceptable <1 Acceptable
10 – 30 Borderline 1–9 Borderline
> 30 Unacceptable >9 Unacceptable
3. EFFECT OF GAGE R&R VARIATION ON PROCESS CAPABILITY INDEX C p
When analyzing process capability the most significant is C p index based on process dispersion. In
order to be able to provide notion on actual process capability, gage R&R must be able to detect any
deviation in monitored process or product. Further analysis shows the relationship of the observed
process capability index C pTV that results from total variability TV and actual index C p , based on
variation of parts in PV process.
C pTV = C p × 1 − (R & R )
2 (9)
Relationship between process capability indices C pTV i C p that depends on quality of gage R&R are
illustrated on Figure 1, and in Table 3.
191
Table 3. Relationship between process capability
indices C pTV and C p
Gage R&R, %
Cp 90% 70% 50% 30% 10%
C pTV
0,5 0,22 0,36 0,43 0,48 0,50
1 0,44 0,71 0,87 0,95 0,99
1,5 0,65 1,07 1,30 1,43 1,49
2 0,87 1,43 1,73 1,91 1,99
2,5 1,09 1,79 2,17 2,38 2,49
3 1,31 2,14 2,60 2,86 2,98
Figure 1. Relationship between process capability
indices C pTV and C p
From the presented results it may be concluded that quality of measurement system significantly
affects process capability index C p . If the observed process capability index C pTV = 1,73, and gage
R&R spends 50 % of total variation or tolerance field, actual process capability index will be as
follows: C p = 2 ,0 . However, if gage R&R spends 10 % of total variation or tolerance field, the
observed process capability index will be C pTV = 1,99 , meaning that process capability estimation is
significantly better. Also, it needs to be emphasized that in case that gage R&R variation is significant
in comparison to the established variation of the parts PV, measurement system will not be able to give
an accurate estimate of process capability.
4. CONCLUSION
Based on conducted analysis it may be concluded that high quality measurement system is essential
for detection and monitoring of process variations. Greater % R&R means greater error in estimating
process capability index C p . Error in estimation increases as the index C p increases. Only high
quality measurement system will be able to provide accurate and precise estimation of process
capability.
5. REFERENCES
[1] Forrest W. Breyfolge III: Implementing Six Sigma, Awiley-Interscience Publication, 1999.
[2] Mudronja V., Lectures in Quality Management, FSB, 2008.
[3] Bass I., Lawton B., Lean Six Sigma, eBook, 2009.
192