Designation: F 1503 – 95 An American National Standard

AMERICAN SOCIETY FOR TESTING AND MATERIALS

100 Barr Harbor Dr., West Conshohocken, PA 19428
Reprinted from the Annual Book of ASTM Standards. Copyright ASTM

Standard Practice for

Machine/Process Potential Study Procedure1
This standard is issued under the fixed designation F 1503; the number immediately following the designation indicates the year of
original adoption or, in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. A
superscript epsilon (e) indicates an editorial change since the last revision or reapproval.

1. Scope have primary responsibility for ensuring that the requirements

1.1 This practice covers the proper method for establishing of this practice are met. The purchaser’s quality assurance
process potentials for new or existing processes. department shall be available to assist on an as-requested basis.
4.3 New manufacturing processes will not be accepted for
2. Referenced Documents use in production with Pp values less than 1.67. If a manufac-
2.1 ASTM Standards: turing process must be conditionally accepted, a process
F 1469 Guide for Conducting a Repeatability and Repro- improvement/product control plan must be developed.
ducibility Study on Test Equipment for Nondestructive 4.3.1 The process improvement/product control plan shall
Testing2 identify specific process improvement activities, which will be
2.2 ASME Standard: implemented to make the process fully capable as well as an
ASME-FAP-1 Quality Assurance Program Requirements interim inspection plan to ensure that nonconforming product
for Fastener Manufacturers and Distributors3 is not shipped to a customer.
4.4 Product Specifications:
3. Terminology
4.4.1 Prior to any process potential study, the product
3.1 Definitions of Terms Specific to This Standard: specifications (nominal dimension and tolerances) must be
3.1.1 bilateral specifications—specifications that have both identified, and an appropriate method of variables type inspec-
upper and lower values. tion selected.
3.1.2 Pp—an index that indicates the variability of the 4.4.2 This practice is limited to bilateral specifications
process with respect to tolerance. whose distributions can be expected to approximate a normal
3.1.3 Ppk—an index of process variability and centering. curve. This practice should not be applied to unilateral speci-
This is a widely-used index which considers the process mean, fications (flatness, concentricity, minimum tensile, maximum
range, and its relation to the specification nominal. hardness, etc.).
3.1.4 process parameters—combination of people, equip-
4.5 Gage Capability Analysis:
ment, materials, methods, and environment that produce out-
put. 4.5.1 All gaging systems used to evaluate product must
3.1.5 unilateral specifications—specifications that have have documentation for a gage repeatability and reproducibil-
only upper or lower values. ity study in accordance with Guide F 1469 before the process
3.1.6 s—an estimate of the standard deviation of a process study is conducted.
characteristic. 4.5.1.1 Gaging systems which consume #10 % of the
applicable product tolerance are considered acceptable.
4. Summary of Practices 4.5.1.2 Gaging systems which consume over 10 to 30 % of
4.1 A process potential study is conducted to provide a level the applicable product tolerance are generally considered to be
of confidence in the ability of a machine/process to meet unacceptable. However, users of this guide may authorize their
engineering specification requirements. This is accomplished use depending on factors such as the criticality of the specifi-
through statistical process control techniques as defined in this cation in question, the cost of alternative gaging systems, and
practice. so forth.
4.2 For new equipment purchases, the purchaser’s manufac- 4.5.1.3 Gaging systems which consume more than 30 % of
turing engineering department, or equivalent discipline, shall the product tolerance are unacceptable and must be replaced.
4.5.2 All gaging systems must be certified as accurate using
1
standards traceable to NIST.
This practice is under the jurisdiction of ASTM Committee F-16 on Fasteners
and is the direct responsibility of Subcommittee F16.93 on Quality Assurance
4.6 Process Parameter Selection:
Provisions for Fasteners. 4.6.1 For studies conducted at the equipment vendor’s
Current edition approved Aug. 15, 1995. Published October 1995. Originally facility, all process parameters (for example, infeed rates,
published as F 1503 – 94. Last previous edition F 1503 – 94.
2 coolant, dies, pressures, fixtures, etc.) must be established and
Annual Book of ASTM Standards, Vol 15.08.
3
Available from American Society of Mechanical Engineers, 345 E. 47th Street, documented prior to the process qualification test so the
New York, NY 10017. requirements of 9.5 can be met.

1
 F 1503
4.6.1.1 Process parameters may not be changed once a 7.2.1.2 A minimum of 25 subgroups are required to estab-
process qualification test has begun. lish control.
4.6.1.2 All process adjustments made during the process 7.2.2 When the quantity of sample measurements cannot be
qualification study must be documented and included with practically obtained, it is permissible to utilize a chart for
information required in Section 10.1 of this practice. individuals and moving ranges, Fig. 2.4
7.2.2.1 A minimum of 25 subgroups are required to estab-
NOTE 1—Process adjustments are defined as those adjustments made by
the process due to internal process gaging (or other sources of feedback lish control.
control), or by the operator as part of the normal operation of process. 7.2.3 After the study is complete, calculate and plot the
control limits, X̄ and R̄ (or MR̄), for each specification
4.6.2 The selection of process parameters is the responsi-
identified in 4.4.1 (see Table 1). If during the study the process
bility of the purchaser’s manufacturing engineering or equiva-
was out of control, the process potential study is not valid. The
lent discipline, or, in some cases, the machine supplier depend-
root cause(s) of the out-of-control condition(s) must be iden-
ing on preestablished contractual agreements.
tified and eliminated and the study repeated.
4.6.2.1 The process parameters selected must be consistent
7.2.3.1 If the out-of-control condition is associated with no
with those intended to be used in production.
more than two subgroups on the range chart, one point on the
4.6.3 Process parameters may be systematically varied after
X̄ or individuals chart and the root cause of the out-of-control
a study is completed and additional process qualification
condition is identified and corrected, new control limits may be
studies performed for process optimization purposes.
calculated by excluding the out-of-control points. A second
5. Significance and Use study is not required.
5.1 This practice is designed to evaluate a machine or 7.2.3.2 In some instances, control chart analysis may reveal
process isolated from its normal operating environment. In its out-of-control conditions that are inherent to the process.
normal operating environment, there would be many sources of Trends due to tool wear or grinding wheel wear are typical
variation that may not exist at a machine builder’s facility; or examples. If the cause of the out-of-control condition is known,
put another way, this study is usually conducted under ideal the out-of-control condition is both repeatable and predictable,
conditions. Therefore, it should be recognized that the results and the condition cannot be eliminated, the process potential
of this practice are usually a “best case” analysis, and allow- study may be considered acceptable and Pp and Ppk values
ances need to be made for sources of variations that may exist calculated in accordance with 8.1-8.3.
TABLE 1 Process Average and Range
at the purchaser’s facility.
5.2 Further comment on the significance of statistical analy- Calculate the average Range (R̄) and the Process Average X̄
sis and capability studies can be found in ASME FAP-1. For the study period, calculate:
R1+ R2+. . .+ Rk
6. Material Selection R̄5 k
6.1 Material (for example, steel slugs, bar, wire, prefinished
X̄1+ X̄2+. . .+ X̄k
parts, etc.) used for process qualification studies shall be
X̄5 k
selected at random. The variability of material used for process
Where k is the number of subgroups, R1 and X̄1 are the range and average of
qualification studies should be consistent with the variability of the first subgroup, R2 and X̄2 are from the second subgroup, etc.
material the machine is likely to see in production.
6.2 Presorting of material is not permissible for process 8. Calculating Results
qualification purposes. 8.1 Estimate the process standard deviation as follows:
6.3 In some cases, process potential results may be influ-
enced by the specific product specifications selected for the s 5 R̄/d2 (1)
study. The specific product selected for qualifying a new
where:
manufacturing process should be based on that which will yield d2 5 constants for sample size 2 to 10, see Table 2.
the most conservative results. If the relationship between 8.2 Calculate Pp by dividing the total product tolerance by
specific product specifications and process potential is un- 6 s.
known, two or more distinct studies should be performed with 8.3 Calculate Ppk as follows:
different products to qualify and accept the new process.
Ppk 5 minimum of ~USL 2 X̄!/3 s or ~ X̄ 2 LSL!/3 s (2)
7. Procedure-Process Potential Study
7.1 Operate the process for a sufficient period of time to where
ensure that the process is stable and all initial setup adjustments USL 5 upper specification limit, and
are complete. LSL 5 lower specification limit.
7.2 Control charting techniques should be utilized to deter- 9. Analysis of Results
mine the stability and capability of the process.
9.1 The qualification of a manufacturing process shall be
7.2.1 When possible, a standard X̄, R chart (Fig. 1) should
based on a review of the statistical parameters Pp and Ppk. Pp
be used with subgroup size n equals 2 through 5.
7.2.1.1 Sampling frequencies should be established to en-
sure that all likely sources of variability occur, and can be 4
Understanding Statistical Process Control, Wheeler and Chambers, Statistical
evaluated within the scope of the process potential study. Process Controls, Inc., 5908 Toole Drive, Suite C, Knoxville, TN 37919.

2
 F 1503

FIG. 1 Variables Control Chart (X̄ and R)

and Ppk are both numerical indexes that provide a measure of TABLE 2 Process Standard Deviation
a process’s variability relative to predefined product
Estimate the process standard deviation (the estimate is shown as ŝ “sigma
specifications. Pp considers the tolerance range only, whereas hat”).
Ppk considers both the tolerance range as well as how close the Using the existing sample size calculate:
process average was to the nominal specification. Pp and Ppk ŝ 5 R̄/d2
Where R̄ is the average of the subgroup ranges (for periods with the ranges in
will have the same numerical value when the process average control) and d2 is a constant varying by sample size, as shown in the table
is centered around nominal. As the process average moves below:
away from nominal, Ppk will decrease. n 2 3 4 5 6 7 8 9 10
d2 1.13 1.69 2.06 2.33 2.53 2.70 2.85 2.97 3.08
9.2 The decision to accept or qualify a manufacturing
process shall be based on the following criteria: 9.2.2 Conditional Acceptance—Ppk equals 1.33 to 1.67.
9.2.1 Accept—Ppk equals 1.67 or greater. Process is capable Process is marginally capable. SPC techniques may be used;
of consistently producing product within specification, if however, special care must be taken to ensure that the process
controlled properly, using statistical process control (SPC) average is as close to nominal as possible. Occasional 100 %
techniques. sorting of product may be required.

3
 F 1503

FIG. 2 Individual and Moving Ranges

9.2.3 Reject—Ppk equals less than 1.33. Process is responsible for reviewing all adjustments made during the
incapable of producing product within specification. This will study and ensuring that the same level of control can/will be
require 100 % sorting by the machine operator. used in production.
9.3 A process with Ppk < 1.33 may also be accepted if both 9.5 If the original process potential study is conducted at the
of the following conditions exist. equipment vendor’s facility, a follow-up study must be
9.3.1 Pp $ 1.67, and performed after the process is set up and running in the
9.3.2 The process is such that the process average can be appropriate manufacturing facility to confirm results.
controlled by the machine operator through normal process
adjustments.
10. Documentation
9.3.3 The requirements identified in 4.3 shall be imposed on
any process that receives conditional acceptance. 10.1 Documentation of each gage repeatability/
9.4 In many cases, capability may vary depending on the reproducibility study and process qualification analysis
degree of control exercised during the study (that is, the type conducted must be forwarded to the purchaser’s quality
and frequency of adjustments made). The purchaser is assurance department for review.

The American Society for Testing and Materials takes no position respecting the validity of any patent rights asserted in connection
with any item mentioned in this standard. Users of this standard are expressly advised that determination of the validity of any such
patent rights, and the risk of infringement of such rights, are entirely their own responsibility.

This standard is subject to revision at any time by the responsible technical committee and must be reviewed every five years and
if not revised, either reapproved or withdrawn. Your comments are invited either for revision of this standard or for additional standards
and should be addressed to ASTM Headquarters. Your comments will receive careful consideration at a meeting of the responsible
technical committee, which you may attend. If you feel that your comments have not received a fair hearing you should make your
views known to the ASTM Committee on Standards, 100 Barr Harbor Drive, West Conshohocken, PA 19428.