You are on page 1of 8

Measurement Systems Analysis

Measurements

Chapter Four

Measurement Systems Analysis

Measurement accuracy and precision

Measurement Systems Analysis

Accuracy and precision

• Measurements are said to be accurate if their tendency is to center around


the actual value of the entity being measured.
• Measurements are precise if they differ from one another by a small
amount.
• What can you say about the causes relating to each type?

Measurement Systems Analysis

Measurement Systems Analysis

Measurement Systems Analysis

Measured Value

Measured
Value = ƒ(TV + Ac + Rep + Rpr)

TV = true value

Ac = gauge accuracy

Rep = gauge repeatability


Rpr = gauge reproducibility

Measurement Systems Analysis

Measurement system components

• Equipment or gage
o Type of gage
 Attribute: go-no go, vision systems
(part present or not present)
 Variable: calipers, probe, coordinate measurement machines
o Unit of measurement - usually at least 1/10 of tolerance
• Operator and operating instructions

Measurement Systems Analysis

Measurement error

• Measurement error is considered to be the difference between a value


measured and the true value.

Measurement Systems Analysis

Types of gage variation

• Systematic variation
o Accuracy - improper calibration
o Reproducibility - different persons using same equipment with
different techniques
• Periodic variation
o Stability - wear, deterioration, environment
• Random variation
o Repeatability (unable to locate part to be measured)

Measurement Systems Analysis

Types of measurement variation


• Accuracy

• Stability

• Reproducibility

• Repeatability

Measurement Systems Analysis

Accuracy

Difference between the true average and the

observed average.

(True average may be obtained by using a more precise


measuring tool)

True average

Observed

average

Accuracy or

mean bias

Measurement Systems Analysis

Stability

Time 1
Time 2

The difference in the average of at least 2 sets of


measurements obtained with a gage over time.

Stability

Measurement Systems Analysis

Reproducibility

Operator B

Operator A

Operator C

True Average

Variation in average of measurements made by different


operators using the same gage measuring the same part.

Measurement Systems Analysis

Repeatability

The random variation in measurements when one operator


uses the same gage to measure the same part several times.

True Average

Observed Average

Repeatability

Measurement Systems Analysis

How do we improve gage capability?


• Reproducibility
o operator training, or
o more clearly define measurement scale available to the operator
• Repeatability
o gage maintenance
o gage redesign to better fit application

R & R Repeatability and


Reproducibility
R&R, GR&R, or gauge R & R is a concept to insure stabile
measurements where a single person gets the exact same results each
and every time they measure and/or collect data measurements. This
can be necessary to ensure data consistency and stability. There are
different ways to perform this. The following is an abbreviated
explanation using the method recommended by the AIAG, (Automotive
Industry Action Group). It is used in most quality plans including six
sigma and ISO9000.

This will give you an approximation of the variation and percent of


process variation for the total measurement system and its component's
repeatability, reproducibility and part to part variations. The formulas to
do this analysis and the proper sequence to follow is below.

Repeatability

EV = Equipment Variation
r = 4.56 for 2 trials, 3.05 for 3 trials

Reproducibility
AV = Appraiser Variation
k = 3.65 for 2 appraisers, 2.7 for 3 appraisers

Repeatability and Reproducibility

Part Variation

PV = Part Variation
Rp = Range of part averages
j= Depends on number of parts

Part 2 3 4 5 6 7 8 9 10
j 3.65 2.7 2.3 2.08 1.93 1.82 1.74 1.67 1.62

Total Variation

TV = Total Variation

Percentage of total variation is calculated using the formulas below

%EV = 100(EV/TV)
%AV = 100(AV/TV)
%R&R = 100(R&R/TV)
%PV = 100(PV/TV)
Guidelines for acceptable results are...

< 10% Satisfactory


10%- May be satisfactory. Depends on the magnitude of the use, cost
30% of new gauges, cost of repairs, etc.
> 30% Unsatisfactory. Take corrective action.

Gauge Repeatability and Reproducibility, or GR&R, is a measure of the capability of a gauge


or gage to obtain the same measurement reading every time the measurement process is
undertaken for the same characteristic or parameter. In other words, GR&R indicates the
consistency and stability of a measuring equipment. The ability of a measuring device to provide
consistent measurement data is important in the control of any process.

Mathematically, GR&R is actually a measure of the variation of a gage's measurement, and not
of its stability. An engineer must therefore strive to minimize the GR&R numbers of his or her
measuring equipment, since a high GR&R number indicates instability and is thus undesirable.

As its name implies, GR&R (or simply 'R&R') has two major components, namely, repeatability
and reproducibility. Repeatability is the ability of the same gage to give consistent measurement
readings no matter how many times the same operator of the gage repeats the measurement
process. Reproducibility, on the other hand, is the ability of the same gage to give consistent
measurement readings regardless of who performs the measurements. The evaluation of a
gage's reproducibility, therefore, requires measurement readings to be acquired by different
operators under the same conditions.

Of course, in the real world, there are no existing gages or measuring devices that give exactly
the same measurement readings all the time for the same parameter. There are five (5) major
elements of a measurement system, all of which contribute to the variability of a measurement
process: 1) the standard; 2) the workpiece; 3) the instrument; 4) the people; and 5) the
environment.

All of these factors affect the measurement reading acquired during each measurement cycle,
although to varying degrees. Measurement errors, therefore, can only be minimized if the errors
or variations contributed individually by each of these factors can also be minimized. Still, the
gage is at the center of any measurement process, so its proper design and usage must be
ensured to optimize its repeatability and reproducibility.

There are various ways by which the R&R of an instrument may be assessed, one of which is
outlined below. This method, which is based on the method recommended by the Automotive
Industry Action Group (AIAG), first computes for variations due to the measuring equipment and
its operators. The over-all GR&R is then computed from these component variations.

Equipment Variation, or EV, represents the repeatability of the measurement process. It is


calculated from measurement data obtained by the same operator from several cycles of
measurements, or trials, using the same equipment. Appraiser Variation or AV, represents the
reproducibility of the measurement process. It is calculated from measurement data obtained by
different operators or appraisers using the same equipment under the same conditions. The
R&R, is just the combined effect of EV and AV.

It must be noted that measurement variations are caused not just by EV and AV, but by Part
Variation as well, or PV. PV represents the effect of the variation of parts being measured on the
measurement process, and is calculated from measurement data obtained from several parts.

Thus, the Total Variation (TV), or the over-all variation exhibited by the measurement system,
consists of the effects of both R&R and PV. TV is equal to the square root of the sum of (R&R)2
and (PV)2 square, i.e.,
TV = √ (R&R)2 + PV2.

In a GR&R report, the final results are often expressed as %EV, %AV, %R&R, and %PV, which
are simply the ratios of EV, AV, R&R, and PV to TV expressed in %. Thus,
%EV=(EV/TV)x100%; %AV=(AV/TV)x100%; %R&R=(R&R/TV)x100%; and
%PV=(PV/TV)x100%. The gage is good if its %R&R is less than 10%. A %R&R between 10%
to 30% may also be acceptable, depending on what it would take to improve the R&R. A %R&R
of more than 30%, however, should prompt the process owner to investigate how the R&R of the
gage can be further improved