SIST ISO 22514-1:2015
Statistical methods in process management - Capability and performance - Part 1: General principles and concepts
Statistical methods in process management - Capability and performance - Part 1: General principles and concepts
This part of ISO 22514 describes the fundamental principles of capability and performance of
manufacturing processes. It has been prepared to provide guidance about circumstances where a
capability study is demanded or necessary to determine if the output from a manufacturing process
or the production equipment (a production machine) is acceptable according to appropriate criteria.
Such circumstances are common in quality control when the purpose for the study is part of some
kind of production acceptance. These studies can also be used when diagnosis is required concerning a
production output or as part of a problem solving effort. The methods are very versatile and have been
applied for many situations.
This part of ISO 22514 is applicable to the following:
— organizations seeking confidence that their product characteristics requirements are fulfilled;
— organizations seeking confidence from their suppliers that their product specifications are and will
be satisfied;
— those internal or external to the organization who audit it for conformity with the product
requirements;
— those internal to the organization who deal with analysing and evaluating the existing production
situation to identify areas for process improvement.
Méthodes statistiques dans la gestion de processus - Aptitude et performance - Partie 1: Principes et concepts généraux
L'ISO 22514-1:2014 d�crit les principes fondamentaux de l'aptitude et de la performance des processus de fabrication. Elle a �t� �labor�e pour fournir des recommandations concernant les circonstances dans lesquelles une �tude d'aptitude est exig�e ou n�cessaire pour d�terminer si le r�sultat d'un processus de fabrication ou le mat�riel de production (une machine de fabrication) est acceptable selon des crit�res appropri�s. Ces circonstances sont courantes dans le processus de contr�le de la qualit�, lorsque l'objet de l'�tude fait partie int�grante d'un certain type d'acceptation de la production. Ces �tudes peuvent �galement �tre utilis�es lorsqu'un diagnostic est requis concernant le rendement d'une production ou comme partie int�grante d'une d�marche de r�solution de probl�mes. Les m�thodes utilis�es, tr�s polyvalentes, ont �t� appliqu�es dans de nombreuses situations.
L'ISO 22514-1:2014 est applicable:
? aux organismes qui cherchent � s'assurer que les exigences relatives aux caract�ristiques de leurs produits sont satisfaites;
? aux organismes qui cherchent � s'assurer que leurs fournisseurs satisfont et satisferont aux sp�cifications de leurs produits;
? � ceux, en interne ou � l'ext�rieur de l'organisme, qui auditent ce dernier en termes de conformit� aux exigences relatives au produit;
? � ceux, � l'int�rieur de l'organisme, qui analysent et �valuent la situation de production existante pour identifier les secteurs d'am�lioration du processus.
Statistične metode za obvladovanje procesov - Sposobnost in delovanje - 1. del: Splošna načela in pojmi
Ta del standarda ISO 22514 opisuje temeljna načela sposobnosti in delovanja proizvodnih procesov. Namenjen je ponujanju smernic o okoliščinah, pri katerih je zahtevana ali potrebna študija sposobnosti, da se določi, ali je rezultat proizvodnega procesa ali proizvodne opreme (proizvodnega stroja) sprejemljiv glede na ustrezne kriterije. Take okoliščine so pri nadzoru kakovosti pogoste, kadar je namen študije del neke vrste sprejemljivosti proizvodnje. Te študije je mogoče uporabiti tudi, kadar je potrebna diagnoza obsega proizvodnje ali kot del reševanja težav. Te metode so zelo raznolike in so bile uporabljene v različnih situacijah.
Ta del standarda ISO 22514 se uporablja za:
– organizacije, ki želijo biti prepričane, da so izpolnjene njihove zahteve glede lastnosti izdelkov;
– organizacije, ki želijo zaupati svojim dobaviteljem, da so in bodo izpolnjene njihove zahteve glede lastnosti izdelkov;
– notranje in zunanje člane organizacije, ki izvajajo presoje organizacije glede skladnosti z lastnostmi izdelkov;
– notranje člane organizacije, ki analizirajo in vrednotijo obstoječo proizvodnjo, da bi prepoznali področja, na katerih so možne izboljšave postopka.
General Information
Relations
Buy Standard
Standards Content (Sample)
SLOVENSKI STANDARD
SIST ISO 22514-1:2015
01-marec-2015
1DGRPHãþD
SIST ISO 22514-1:2010
6WDWLVWLþQHPHWRGH]DREYODGRYDQMHSURFHVRY6SRVREQRVWLQGHORYDQMHGHO
6SORãQDQDþHODLQSRMPL
Statistical methods in process management - Capability and performance - Part 1:
General principles and concepts
Méthodes statistiques dans la gestion de processus - Aptitude et performance - Partie 1:
Principes et concepts généraux
Ta slovenski standard je istoveten z: ISO 22514-1:2014
ICS:
03.120.30 8SRUDEDVWDWLVWLþQLKPHWRG Application of statistical
methods
SIST ISO 22514-1:2015 en
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.
---------------------- Page: 1 ----------------------
SIST ISO 22514-1:2015
---------------------- Page: 2 ----------------------
SIST ISO 22514-1:2015
INTERNATIONAL ISO
STANDARD 22514-1
Second edition
2014-06-01
Statistical methods in process
management — Capability and
performance —
Part 1:
General principles and concepts
Méthodes statistiques dans la gestion de processus — Aptitude et
performance —
Partie 1: Principes et concepts généraux
Reference number
ISO 22514-1:2014(E)
©
ISO 2014
---------------------- Page: 3 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
COPYRIGHT PROTECTED DOCUMENT
© ISO 2014
All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form
or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior
written permission. Permission can be requested from either ISO at the address below or ISO’s member body in the country of
the requester.
ISO copyright office
Case postale 56 • CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Published in Switzerland
ii © ISO 2014 – All rights reserved
---------------------- Page: 4 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
3.1 Basic terms . 1
3.2 Performance, measures, and indices. 7
3.3 Capability, measures, and indices .10
4 Symbols and abbreviated terms .13
5 Pre-conditions for application .13
5.1 Aspects about establishing specifications .13
5.2 Distribution and sample size .13
5.3 Materials used in studies . .14
5.4 Special circumstances .14
6 Collection of data .14
6.1 Traceability of data .14
6.2 Measurement uncertainty .14
6.3 Data recording .15
6.4 Outliers .15
7 Performance, capability, and process analysis .15
7.1 Six different types of performance and capability .15
7.2 Basic considerations .16
7.3 Machine performance .18
7.4 Process performance and process capability .19
7.5 Position performance .19
7.6 Measurement process capability . .20
7.7 Performance and capability indices .21
8 Results of use .21
9 Benefits of use .22
10 Limitations of use .22
Bibliography .23
© ISO 2014 – All rights reserved iii
---------------------- Page: 5 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation on the meaning of ISO specific terms and expressions related to conformity
assessment, as well as information about ISO’s adherence to the WTO principles in the Technical Barriers
to Trade (TBT) see the following URL: Foreword - Supplementary information
The committee responsible for this document is ISO/TC 69, Applications of statistical methods,
Subcommittee 4, Applications of statistical methods in process management.
This second edition cancels and replaces the first edition (ISO 22514-1:2009), which has been technically
revised.
ISO 22514 consists of the following parts, under the general title Statistical methods in process
management — Capability and performance:
— Part 1: General principles and concepts
— Part 2: Process capability and performance of time-dependent process models
— Part 3: Machine performance studies for measured data on discrete parts
— Part 4: Process capability estimates and performance measures [Technical Report]
— Part 6: Process capability statistics for characteristics following a multivariate normal distribution
— Part 7: Capability of measurement processes
— Part 8: Machine performance of a multi-state production process
An additional part, dealing with process capability statistics for attribute characteristics, is planned.
iv © ISO 2014 – All rights reserved
---------------------- Page: 6 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
Introduction
This general introduction to capability treats the subject’s capability and performance in a general
way. To understand fully the concepts, it would be helpful to consult ISO 22514-2, ISO 22514-3, and
ISO/TR 22514-4. These documents extend this introductory explanation to more specific uses of the
procedures.
A process can be either a discrete process or a continuous process. A discrete process generates a
sequence of distinguishable items and a continuous process generates a continuous product (e.g. a lane
of paper).
The purpose of a process is to manufacture a product or perform a service, which satisfies a set of
preset specifications. The specifications for a process under investigation are defined for one or more
characteristics of the product or service. However, in process performance or capability, only one
characteristic is considered at a time. The characteristic can either be measurable, countable, or it can
be a property. The process is, thus, generating either a discrete or a continuous stochastic process. The
discrete process can either be a process of real numbers, a process of natural numbers, or a process
telling which event from a set of events has occurred for the individual items. As an example, the set of
events for the individual items could be {colour acceptable; colour not acceptable}.
In general, the notation for a discrete stochastic process is {X }, where X is the outcome of element no. i
i i
in the process. In case the characteristic is a property X , it is a value given to each of the events in the set
i
of events used for characterizing the process. For a discrete process, the index i is normally the number
of the item in the generated sequence of items. However, sometimes it might be more convenient to use
the time from a fixed point as the index. When the process is continuous, a number of possibilities exist
for the index depending on the nature of the product. When the product is e.g. a lane of paper, the index
could be the length from a starting point or it could be the time from a fixed point.
It should be noted that normally a serial correlation exists in a stochastic process.
A stochastic process is either stationary or non-stationary. The stringent definition of a stationary
stochastic process will not be given here. However, for a stationary process a distribution exists for X ,
i
which is independent of i.
Stochastic processes that satisfy the specifications are either stationary processes or well-defined non-
stationary processes (e.g. periodic processes).
To evaluate a process, a performance study is performed. In fact, a performance study starts as a
theoretical study of all the elements in the process before the process is physically implemented. When
the parameters of the various stages in the process have been analysed and redefined, the process is
implemented (might be only as a test process).
Based on sampling from the implemented process, the numerical part of the performance study of the
process is started. A number of questions concerning the process will, beyond any reasonable doubt, be
answered correctly. The most important question to be answered is whether the process is a stationary
process, which is stable or predictable for a reasonable period. For the process, it is then important to
identify the probability distribution of the process and to obtain estimates of the distribution parameters
with a reasonable small variance. Based on this information, the next stage in the performance study
would be to map the properties of the characteristics under investigation and decide whether they are
acceptable. If the properties cannot be accepted, the parameters of the process itself will be changed in
order to obtain a process with acceptable properties.
Consider a well-defined and implemented process that has been accepted using a performance study.
The next stage for the process would then be to ensure that the parameters of the process and thus, of
the stochastic process do not change, or changes in a predicted way. This is performed by defining a
suitable capability study.
These studies of performance and capability indices are today more and more used to assess production
equipment, a process, or even measurement equipment relative to specification criteria. Different types
of studies are used depending on the circumstances.
© ISO 2014 – All rights reserved v
---------------------- Page: 7 ----------------------
SIST ISO 22514-1:2015
---------------------- Page: 8 ----------------------
SIST ISO 22514-1:2015
INTERNATIONAL STANDARD ISO 22514-1:2014(E)
Statistical methods in process management — Capability
and performance —
Part 1:
General principles and concepts
1 Scope
This part of ISO 22514 describes the fundamental principles of capability and performance of
manufacturing processes. It has been prepared to provide guidance about circumstances where a
capability study is demanded or necessary to determine if the output from a manufacturing process
or the production equipment (a production machine) is acceptable according to appropriate criteria.
Such circumstances are common in quality control when the purpose for the study is part of some
kind of production acceptance. These studies can also be used when diagnosis is required concerning a
production output or as part of a problem solving effort. The methods are very versatile and have been
applied for many situations.
This part of ISO 22514 is applicable to the following:
— organizations seeking confidence that their product characteristics requirements are fulfilled;
— organizations seeking confidence from their suppliers that their product specifications are and will
be satisfied;
— those internal or external to the organization who audit it for conformity with the product
requirements;
— those internal to the organization who deal with analysing and evaluating the existing production
situation to identify areas for process improvement.
2 Normative references
The following documents, in whole or in part, are normatively referenced in this document and are
indispensable for its application. For dated references, only the edition cited applies. For undated
references, the latest edition of the referenced document (including any amendments) applies.
ISO 1101, Geometrical product specifications (GPS) — Geometrical tolerancing — Tolerances of form,
orientation, location and run-out
ISO 22514-7, Statistical methods in process management — Capability and performance — Part 7: Capability
of measurement processes
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
3.1 Basic terms
3.1.1
requirement
need or expectation that is stated, generally implied, or obligatory
[SOURCE: ISO 9000:2005, 3.1.2]
© ISO 2014 – All rights reserved 1
---------------------- Page: 9 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
3.1.2
process
set of inter-related or interacting activities which transforms inputs into outputs
Note 1 to entry: Inputs to a process are generally outputs from other processes.
Note 2 to entry: Processes in an organization are generally planned and carried out under controlled conditions
to add value.
[SOURCE: ISO 3534-2:2006, 2.1.1, modified]
3.1.3
system
set of interrelated or interacting elements
[SOURCE: ISO 9000:2005, 3.2.1]
3.1.4
product
result of a process
Note 1 to entry: Four generic product categories are
— services (e.g. transport),
— software (e.g. computer program),
— hardware (e.g. engine mechanical part), and
— processed materials (e.g. lubricant).
Many products comprise elements belonging to different generic product categories. What the product is then
called depends on the dominant element.
Note 2 to entry: In mathematics, the concept of product is limited to the result of multiplication.
[SOURCE: ISO 3534-2:2006, 1.2.32]
3.1.5
characteristic
distinguishing feature (of an item)
[SOURCE: ISO 9000:2005, 3.5.1, modified]
Note 1 to entry: Item is defined in ISO 3534-2:2006, definition 1.2.11.
3.1.6
quality
degree to which a set of inherent characteristics (3.1.5) of a product (3.1.4) fulfils requirements (3.1.1) of
customers and other interested parties
Note 1 to entry: In ISO 9000:2005, 3.1.1, quality is defined without specification of who defines the requirements.
3.1.7
product characteristic
inherent characteristic (3.1.5) of a product (3.1.2)
Note 1 to entry: Product characteristics can be either quantitative or qualitative.
Note 2 to entry: The product characteristic can be multidimensional.
2 © ISO 2014 – All rights reserved
---------------------- Page: 10 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
3.1.8
process characteristic
inherent characteristic (3.1.5) of a process (3.1.4)
Note 1 to entry: Process characteristics can be either quantitative or qualitative.
Note 2 to entry: The process characteristic can be multidimensional.
3.1.9
quality characteristic
inherent characteristic (3.1.5) of a product (3.1.4), process (3.1.2), or system (3.1.3) related to a requirement
(3.1.1)
Note 1 to entry: Quality characteristics can be either quantitative or qualitative.
Note 2 to entry: The quality characteristic can be multidimensional.
Note 3 to entry: Often, there is a strong correlation between a process characteristic and a product characteristic,
which is realized by the process. In principle, however, the individual requirement to the process characteristic and
the individual requirement to the product characteristic are different. Each of these both individual requirements
is the part of the quality requirement for the process and the part of the quality requirement for the product,
respectively.
3.1.10
specification
document stating requirements (3.1.1)
Note 1 to entry: A specification can be related to activities (e.g. procedure document, process specification, and
test specification), or products (3.1.4) (e.g. product specification, performance specification, and drawing).
[SOURCE: ISO 9000:2005, 3.7.3]
3.1.11
specification limit
limiting value stated for a characteristic (3.1.5)
[SOURCE: ISO 3534-2:2006, 3.1.3]
Note 1 to entry: Sometimes specification limits are called tolerance limits.
3.1.12
upper specification limit
U
specification limit (3.1.11) that defines the highest value a quality characteristic can have and still be
considered conforming
Note 1 to entry: The preferred symbol for upper specification limit is U.
[SOURCE: ISO 3534-2:2006, 3.1.4, modified]
3.1.13
lower specification limit
L
specification limit (3.1.11) that defines the lowest value a quality characteristic might have and still be
considered conforming
Note 1 to entry: The preferred symbol for lower specification limit is L.
[SOURCE: ISO 3534-2:2006, 3.1.5, modified]
© ISO 2014 – All rights reserved 3
---------------------- Page: 11 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
3.1.14
specification interval
tolerance interval
tolerance zone
interval between upper and lower specification limits (3.1.11)
Note 1 to entry: This term is completely different from a statistical tolerance interval, which is an interval with
stochastic borders.
3.1.15
target value
T
preferred or reference value of a characteristic (3.1.5) stated in a specification (3.1.10)
[SOURCE: ISO 3534-2:2006, 3.1.2]
3.1.16
nominal value
reference value of a characteristic (3.1.5) stated in a specification
Note 1 to entry: In ISO 3534-2, nominal value and target value are synonyms with target value as the preferred
term. There is a need to distinguish the reference value in a specification and a preferred value used in production.
3.1.17
actual value
value of a quantity in a characteristic (3.1.5)
3.1.18
variation
difference between values of a characteristic (3.1.5)
Note 1 to entry: Variation is often expressed as a variance or standard deviation.
[SOURCE: ISO 3534-2:2006, 2.2.1]
3.1.19
random cause
common cause
chance cause
source of process variation (3.1.18) that is inherent in a process (3.1.2) over time
Note 1 to entry: In a process subject only to random cause variation, the variation is predictable within statistically
established limits.
Note 2 to entry: The reduction of these causes gives rise to process improvement. However, the extent of their
identification, reduction and removal is the subject of cost/benefit analysis in terms of technical tractability and
economics.
[SOURCE: ISO 3534-2:2006, 2.2.5]
3.1.20
product characteristic in control
product characteristic (3.1.7) parameter of the distribution of the characteristic values of which
practically do not change or do change only in a known manner or within known limits
3.1.21
stable process
process in a state of statistical control
process (3.1.2) subject only to random causes (3.1.19)
Note 1 to entry: A production in control is a production with processes in control.
4 © ISO 2014 – All rights reserved
---------------------- Page: 12 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
Note 2 to entry: A stable process will generally behave as though the samples from the process at any time are
simple random samples from the same population.
Note 3 to entry: This state does not imply that the random variation is large or small, within or outside of
specification, but rather that the variation is predictable using statistical techniques.
[SOURCE: ISO 3534-2:2006, 2.2.7, modified]
3.1.22
distribution of a product characteristic
information on the probabilistic behaviour of a product characteristic (3.1.7)
Note 1 to entry: The distribution contains the numerical information about the product characteristic except for
the serial order in which the items have been produced.
Note 2 to entry: The distribution of product characteristic exists whether the product characteristic is being
recorded or not, and it depends on technical conditions such as input batches, tools, operators, etc.
Note 3 to entry: If information about the distribution of product characteristic is desired data must be collected.
The distribution that is observed depends in addition to the technical conditions (see Note 2) and the following
conditions pertaining to the data collection:
— the measurement;
— the time interval over which the sampling takes place;
— the frequency of sampling.
The technical conditions (see Note 2) and the conditions of the data collection shall always be specified.
Note 4 to entry: The distribution of the product characteristic can be represented in any of the ways distributions
and data from distributions are represented. The histogram is frequently used for data from a distribution
whereas the density function is frequently used for a model of the distribution of the product characteristic.
Note 5 to entry: In the following clauses, the distribution of the product characteristic will be considered under
different but well-defined conditions, such as performance and capability, where performance is the least
restrictive.
3.1.23
class of distributions
particular family of distributions (3.1.22) each member of which has the same common attributes by
which the family is fully specified
EXAMPLE 1 The class of normal distributions where the unknown parameters are the mean and the standard
deviation. Often, the class of normal distributions is referred to simply as the normal distribution.
EXAMPLE 2 Three parameters, multi-shaped, Weibull distribution with parameters, location, shape, and scale.
EXAMPLE 3 The unimodal continuous distributions.
Note 1 to entry: The class of distributions can often be fully specified through the values of appropriate parameters.
[SOURCE: ISO 3534-2:2006, 2.5.2, modified]
3.1.24
distribution model of the product characteristic
specified distribution (3.1.22) or class of distributions (3.1.23)
EXAMPLE 1 A model for the distribution of a product characteristic, such as the diameter of a bolt, might be
the normal distribution with mean 15 mm and standard deviation 0,05 mm. Here the model is a fully specified
distribution.
EXAMPLE 2 A model for the same situation as in EXAMPLE 1 could be the class of normal distributions without
attempting to specify a particular distribution. Here the model is the class of normal distributions.
© ISO 2014 – All rights reserved 5
---------------------- Page: 13 ----------------------
SIST ISO 22514-1:2015
ISO 22514-1:2014(E)
[SOURCE: ISO 3534-2:2006, 2.5.3]
3.1.25
reference limits of the product characteristic
X , X
0,135 % 99,865 %
quantile of the distribution of the product characteristic (3.1.22)
EXAMPLE If the distribution of the product characteristic is normal with mean μ and standard deviation σ,
the limits are μ ± 3σ if traditional 0,135 % and 99,865 % quantiles are used.
Note 1 to entry: The conditions of the distribution of the product characteristic shall be specified, see Note 2 and
Note 3 of 3.1.22.
Note 2 to entry: Traditionally the 0,135 % and 99,865 % quantiles have been used.
3.1.26
reference interval of a product characteristic
interval bounded by the 99,865 % distribution quantile, X , and the 0,135 % distribution quantile,
99,865 %
X
0,135 %
EX AMPLE 1 In a normal distribution with mean μ and standard deviation σ, the reference interval corresponding
to the traditional 0,135 % and 99,865 % quantiles has limits μ ± 3σ, and has length 6σ.
EXAMPLE 2 For a non-normal distribution, the reference interval can be estimated by means of appropriate
probability papers (e.g. log-normal) or from the sample kurtosis and sample skewness using the methods
described in ISO/TR 22514-4.
Note 1 to entry: The interval can be expressed by X , X , quantiles and the length of the interval is
0,135 % 99,865 %
X , − X .
99,865 % 0,135 %
Note 2 to entry: This term is used only as an arbitrary, but standardized, basis for defining the process performance
index (3.2.3) and process capability index (3.3.6). It is sometimes, incorrectly, referred to as a “natural” interval.
Note 3 to entry: For a normal distribution, the length of the reference interval can be expressed in terms of six
standard deviations, 6σ, or 6S, when σ is estimated from a sample.
Note 4 to entry: For a non-normal distribution, the length of the reference interval can be estimated by means of
appropriate software or probability plot (e.g. log-normal) or from the sample kurtosis and sample skewness using
the methods described in ISO/TR 22514-4.
Note 5 to entry: A quantile or fractile indicates a division of a distribution into equal units or fractions, e.g
...
INTERNATIONAL ISO
STANDARD 22514-1
Second edition
2014-06-01
Statistical methods in process
management — Capability and
performance —
Part 1:
General principles and concepts
Méthodes statistiques dans la gestion de processus — Aptitude et
performance —
Partie 1: Principes et concepts généraux
Reference number
ISO 22514-1:2014(E)
©
ISO 2014
---------------------- Page: 1 ----------------------
ISO 22514-1:2014(E)
COPYRIGHT PROTECTED DOCUMENT
© ISO 2014
All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form
or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior
written permission. Permission can be requested from either ISO at the address below or ISO’s member body in the country of
the requester.
ISO copyright office
Case postale 56 • CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Published in Switzerland
ii © ISO 2014 – All rights reserved
---------------------- Page: 2 ----------------------
ISO 22514-1:2014(E)
Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
3.1 Basic terms . 1
3.2 Performance, measures, and indices. 7
3.3 Capability, measures, and indices .10
4 Symbols and abbreviated terms .13
5 Pre-conditions for application .13
5.1 Aspects about establishing specifications .13
5.2 Distribution and sample size .13
5.3 Materials used in studies . .14
5.4 Special circumstances .14
6 Collection of data .14
6.1 Traceability of data .14
6.2 Measurement uncertainty .14
6.3 Data recording .15
6.4 Outliers .15
7 Performance, capability, and process analysis .15
7.1 Six different types of performance and capability .15
7.2 Basic considerations .16
7.3 Machine performance .18
7.4 Process performance and process capability .19
7.5 Position performance .19
7.6 Measurement process capability . .20
7.7 Performance and capability indices .21
8 Results of use .21
9 Benefits of use .22
10 Limitations of use .22
Bibliography .23
© ISO 2014 – All rights reserved iii
---------------------- Page: 3 ----------------------
ISO 22514-1:2014(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation on the meaning of ISO specific terms and expressions related to conformity
assessment, as well as information about ISO’s adherence to the WTO principles in the Technical Barriers
to Trade (TBT) see the following URL: Foreword - Supplementary information
The committee responsible for this document is ISO/TC 69, Applications of statistical methods,
Subcommittee 4, Applications of statistical methods in process management.
This second edition cancels and replaces the first edition (ISO 22514-1:2009), which has been technically
revised.
ISO 22514 consists of the following parts, under the general title Statistical methods in process
management — Capability and performance:
— Part 1: General principles and concepts
— Part 2: Process capability and performance of time-dependent process models
— Part 3: Machine performance studies for measured data on discrete parts
— Part 4: Process capability estimates and performance measures [Technical Report]
— Part 6: Process capability statistics for characteristics following a multivariate normal distribution
— Part 7: Capability of measurement processes
— Part 8: Machine performance of a multi-state production process
An additional part, dealing with process capability statistics for attribute characteristics, is planned.
iv © ISO 2014 – All rights reserved
---------------------- Page: 4 ----------------------
ISO 22514-1:2014(E)
Introduction
This general introduction to capability treats the subject’s capability and performance in a general
way. To understand fully the concepts, it would be helpful to consult ISO 22514-2, ISO 22514-3, and
ISO/TR 22514-4. These documents extend this introductory explanation to more specific uses of the
procedures.
A process can be either a discrete process or a continuous process. A discrete process generates a
sequence of distinguishable items and a continuous process generates a continuous product (e.g. a lane
of paper).
The purpose of a process is to manufacture a product or perform a service, which satisfies a set of
preset specifications. The specifications for a process under investigation are defined for one or more
characteristics of the product or service. However, in process performance or capability, only one
characteristic is considered at a time. The characteristic can either be measurable, countable, or it can
be a property. The process is, thus, generating either a discrete or a continuous stochastic process. The
discrete process can either be a process of real numbers, a process of natural numbers, or a process
telling which event from a set of events has occurred for the individual items. As an example, the set of
events for the individual items could be {colour acceptable; colour not acceptable}.
In general, the notation for a discrete stochastic process is {X }, where X is the outcome of element no. i
i i
in the process. In case the characteristic is a property X , it is a value given to each of the events in the set
i
of events used for characterizing the process. For a discrete process, the index i is normally the number
of the item in the generated sequence of items. However, sometimes it might be more convenient to use
the time from a fixed point as the index. When the process is continuous, a number of possibilities exist
for the index depending on the nature of the product. When the product is e.g. a lane of paper, the index
could be the length from a starting point or it could be the time from a fixed point.
It should be noted that normally a serial correlation exists in a stochastic process.
A stochastic process is either stationary or non-stationary. The stringent definition of a stationary
stochastic process will not be given here. However, for a stationary process a distribution exists for X ,
i
which is independent of i.
Stochastic processes that satisfy the specifications are either stationary processes or well-defined non-
stationary processes (e.g. periodic processes).
To evaluate a process, a performance study is performed. In fact, a performance study starts as a
theoretical study of all the elements in the process before the process is physically implemented. When
the parameters of the various stages in the process have been analysed and redefined, the process is
implemented (might be only as a test process).
Based on sampling from the implemented process, the numerical part of the performance study of the
process is started. A number of questions concerning the process will, beyond any reasonable doubt, be
answered correctly. The most important question to be answered is whether the process is a stationary
process, which is stable or predictable for a reasonable period. For the process, it is then important to
identify the probability distribution of the process and to obtain estimates of the distribution parameters
with a reasonable small variance. Based on this information, the next stage in the performance study
would be to map the properties of the characteristics under investigation and decide whether they are
acceptable. If the properties cannot be accepted, the parameters of the process itself will be changed in
order to obtain a process with acceptable properties.
Consider a well-defined and implemented process that has been accepted using a performance study.
The next stage for the process would then be to ensure that the parameters of the process and thus, of
the stochastic process do not change, or changes in a predicted way. This is performed by defining a
suitable capability study.
These studies of performance and capability indices are today more and more used to assess production
equipment, a process, or even measurement equipment relative to specification criteria. Different types
of studies are used depending on the circumstances.
© ISO 2014 – All rights reserved v
---------------------- Page: 5 ----------------------
INTERNATIONAL STANDARD ISO 22514-1:2014(E)
Statistical methods in process management — Capability
and performance —
Part 1:
General principles and concepts
1 Scope
This part of ISO 22514 describes the fundamental principles of capability and performance of
manufacturing processes. It has been prepared to provide guidance about circumstances where a
capability study is demanded or necessary to determine if the output from a manufacturing process
or the production equipment (a production machine) is acceptable according to appropriate criteria.
Such circumstances are common in quality control when the purpose for the study is part of some
kind of production acceptance. These studies can also be used when diagnosis is required concerning a
production output or as part of a problem solving effort. The methods are very versatile and have been
applied for many situations.
This part of ISO 22514 is applicable to the following:
— organizations seeking confidence that their product characteristics requirements are fulfilled;
— organizations seeking confidence from their suppliers that their product specifications are and will
be satisfied;
— those internal or external to the organization who audit it for conformity with the product
requirements;
— those internal to the organization who deal with analysing and evaluating the existing production
situation to identify areas for process improvement.
2 Normative references
The following documents, in whole or in part, are normatively referenced in this document and are
indispensable for its application. For dated references, only the edition cited applies. For undated
references, the latest edition of the referenced document (including any amendments) applies.
ISO 1101, Geometrical product specifications (GPS) — Geometrical tolerancing — Tolerances of form,
orientation, location and run-out
ISO 22514-7, Statistical methods in process management — Capability and performance — Part 7: Capability
of measurement processes
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
3.1 Basic terms
3.1.1
requirement
need or expectation that is stated, generally implied, or obligatory
[SOURCE: ISO 9000:2005, 3.1.2]
© ISO 2014 – All rights reserved 1
---------------------- Page: 6 ----------------------
ISO 22514-1:2014(E)
3.1.2
process
set of inter-related or interacting activities which transforms inputs into outputs
Note 1 to entry: Inputs to a process are generally outputs from other processes.
Note 2 to entry: Processes in an organization are generally planned and carried out under controlled conditions
to add value.
[SOURCE: ISO 3534-2:2006, 2.1.1, modified]
3.1.3
system
set of interrelated or interacting elements
[SOURCE: ISO 9000:2005, 3.2.1]
3.1.4
product
result of a process
Note 1 to entry: Four generic product categories are
— services (e.g. transport),
— software (e.g. computer program),
— hardware (e.g. engine mechanical part), and
— processed materials (e.g. lubricant).
Many products comprise elements belonging to different generic product categories. What the product is then
called depends on the dominant element.
Note 2 to entry: In mathematics, the concept of product is limited to the result of multiplication.
[SOURCE: ISO 3534-2:2006, 1.2.32]
3.1.5
characteristic
distinguishing feature (of an item)
[SOURCE: ISO 9000:2005, 3.5.1, modified]
Note 1 to entry: Item is defined in ISO 3534-2:2006, definition 1.2.11.
3.1.6
quality
degree to which a set of inherent characteristics (3.1.5) of a product (3.1.4) fulfils requirements (3.1.1) of
customers and other interested parties
Note 1 to entry: In ISO 9000:2005, 3.1.1, quality is defined without specification of who defines the requirements.
3.1.7
product characteristic
inherent characteristic (3.1.5) of a product (3.1.2)
Note 1 to entry: Product characteristics can be either quantitative or qualitative.
Note 2 to entry: The product characteristic can be multidimensional.
2 © ISO 2014 – All rights reserved
---------------------- Page: 7 ----------------------
ISO 22514-1:2014(E)
3.1.8
process characteristic
inherent characteristic (3.1.5) of a process (3.1.4)
Note 1 to entry: Process characteristics can be either quantitative or qualitative.
Note 2 to entry: The process characteristic can be multidimensional.
3.1.9
quality characteristic
inherent characteristic (3.1.5) of a product (3.1.4), process (3.1.2), or system (3.1.3) related to a requirement
(3.1.1)
Note 1 to entry: Quality characteristics can be either quantitative or qualitative.
Note 2 to entry: The quality characteristic can be multidimensional.
Note 3 to entry: Often, there is a strong correlation between a process characteristic and a product characteristic,
which is realized by the process. In principle, however, the individual requirement to the process characteristic and
the individual requirement to the product characteristic are different. Each of these both individual requirements
is the part of the quality requirement for the process and the part of the quality requirement for the product,
respectively.
3.1.10
specification
document stating requirements (3.1.1)
Note 1 to entry: A specification can be related to activities (e.g. procedure document, process specification, and
test specification), or products (3.1.4) (e.g. product specification, performance specification, and drawing).
[SOURCE: ISO 9000:2005, 3.7.3]
3.1.11
specification limit
limiting value stated for a characteristic (3.1.5)
[SOURCE: ISO 3534-2:2006, 3.1.3]
Note 1 to entry: Sometimes specification limits are called tolerance limits.
3.1.12
upper specification limit
U
specification limit (3.1.11) that defines the highest value a quality characteristic can have and still be
considered conforming
Note 1 to entry: The preferred symbol for upper specification limit is U.
[SOURCE: ISO 3534-2:2006, 3.1.4, modified]
3.1.13
lower specification limit
L
specification limit (3.1.11) that defines the lowest value a quality characteristic might have and still be
considered conforming
Note 1 to entry: The preferred symbol for lower specification limit is L.
[SOURCE: ISO 3534-2:2006, 3.1.5, modified]
© ISO 2014 – All rights reserved 3
---------------------- Page: 8 ----------------------
ISO 22514-1:2014(E)
3.1.14
specification interval
tolerance interval
tolerance zone
interval between upper and lower specification limits (3.1.11)
Note 1 to entry: This term is completely different from a statistical tolerance interval, which is an interval with
stochastic borders.
3.1.15
target value
T
preferred or reference value of a characteristic (3.1.5) stated in a specification (3.1.10)
[SOURCE: ISO 3534-2:2006, 3.1.2]
3.1.16
nominal value
reference value of a characteristic (3.1.5) stated in a specification
Note 1 to entry: In ISO 3534-2, nominal value and target value are synonyms with target value as the preferred
term. There is a need to distinguish the reference value in a specification and a preferred value used in production.
3.1.17
actual value
value of a quantity in a characteristic (3.1.5)
3.1.18
variation
difference between values of a characteristic (3.1.5)
Note 1 to entry: Variation is often expressed as a variance or standard deviation.
[SOURCE: ISO 3534-2:2006, 2.2.1]
3.1.19
random cause
common cause
chance cause
source of process variation (3.1.18) that is inherent in a process (3.1.2) over time
Note 1 to entry: In a process subject only to random cause variation, the variation is predictable within statistically
established limits.
Note 2 to entry: The reduction of these causes gives rise to process improvement. However, the extent of their
identification, reduction and removal is the subject of cost/benefit analysis in terms of technical tractability and
economics.
[SOURCE: ISO 3534-2:2006, 2.2.5]
3.1.20
product characteristic in control
product characteristic (3.1.7) parameter of the distribution of the characteristic values of which
practically do not change or do change only in a known manner or within known limits
3.1.21
stable process
process in a state of statistical control
process (3.1.2) subject only to random causes (3.1.19)
Note 1 to entry: A production in control is a production with processes in control.
4 © ISO 2014 – All rights reserved
---------------------- Page: 9 ----------------------
ISO 22514-1:2014(E)
Note 2 to entry: A stable process will generally behave as though the samples from the process at any time are
simple random samples from the same population.
Note 3 to entry: This state does not imply that the random variation is large or small, within or outside of
specification, but rather that the variation is predictable using statistical techniques.
[SOURCE: ISO 3534-2:2006, 2.2.7, modified]
3.1.22
distribution of a product characteristic
information on the probabilistic behaviour of a product characteristic (3.1.7)
Note 1 to entry: The distribution contains the numerical information about the product characteristic except for
the serial order in which the items have been produced.
Note 2 to entry: The distribution of product characteristic exists whether the product characteristic is being
recorded or not, and it depends on technical conditions such as input batches, tools, operators, etc.
Note 3 to entry: If information about the distribution of product characteristic is desired data must be collected.
The distribution that is observed depends in addition to the technical conditions (see Note 2) and the following
conditions pertaining to the data collection:
— the measurement;
— the time interval over which the sampling takes place;
— the frequency of sampling.
The technical conditions (see Note 2) and the conditions of the data collection shall always be specified.
Note 4 to entry: The distribution of the product characteristic can be represented in any of the ways distributions
and data from distributions are represented. The histogram is frequently used for data from a distribution
whereas the density function is frequently used for a model of the distribution of the product characteristic.
Note 5 to entry: In the following clauses, the distribution of the product characteristic will be considered under
different but well-defined conditions, such as performance and capability, where performance is the least
restrictive.
3.1.23
class of distributions
particular family of distributions (3.1.22) each member of which has the same common attributes by
which the family is fully specified
EXAMPLE 1 The class of normal distributions where the unknown parameters are the mean and the standard
deviation. Often, the class of normal distributions is referred to simply as the normal distribution.
EXAMPLE 2 Three parameters, multi-shaped, Weibull distribution with parameters, location, shape, and scale.
EXAMPLE 3 The unimodal continuous distributions.
Note 1 to entry: The class of distributions can often be fully specified through the values of appropriate parameters.
[SOURCE: ISO 3534-2:2006, 2.5.2, modified]
3.1.24
distribution model of the product characteristic
specified distribution (3.1.22) or class of distributions (3.1.23)
EXAMPLE 1 A model for the distribution of a product characteristic, such as the diameter of a bolt, might be
the normal distribution with mean 15 mm and standard deviation 0,05 mm. Here the model is a fully specified
distribution.
EXAMPLE 2 A model for the same situation as in EXAMPLE 1 could be the class of normal distributions without
attempting to specify a particular distribution. Here the model is the class of normal distributions.
© ISO 2014 – All rights reserved 5
---------------------- Page: 10 ----------------------
ISO 22514-1:2014(E)
[SOURCE: ISO 3534-2:2006, 2.5.3]
3.1.25
reference limits of the product characteristic
X , X
0,135 % 99,865 %
quantile of the distribution of the product characteristic (3.1.22)
EXAMPLE If the distribution of the product characteristic is normal with mean μ and standard deviation σ,
the limits are μ ± 3σ if traditional 0,135 % and 99,865 % quantiles are used.
Note 1 to entry: The conditions of the distribution of the product characteristic shall be specified, see Note 2 and
Note 3 of 3.1.22.
Note 2 to entry: Traditionally the 0,135 % and 99,865 % quantiles have been used.
3.1.26
reference interval of a product characteristic
interval bounded by the 99,865 % distribution quantile, X , and the 0,135 % distribution quantile,
99,865 %
X
0,135 %
EX AMPLE 1 In a normal distribution with mean μ and standard deviation σ, the reference interval corresponding
to the traditional 0,135 % and 99,865 % quantiles has limits μ ± 3σ, and has length 6σ.
EXAMPLE 2 For a non-normal distribution, the reference interval can be estimated by means of appropriate
probability papers (e.g. log-normal) or from the sample kurtosis and sample skewness using the methods
described in ISO/TR 22514-4.
Note 1 to entry: The interval can be expressed by X , X , quantiles and the length of the interval is
0,135 % 99,865 %
X , − X .
99,865 % 0,135 %
Note 2 to entry: This term is used only as an arbitrary, but standardized, basis for defining the process performance
index (3.2.3) and process capability index (3.3.6). It is sometimes, incorrectly, referred to as a “natural” interval.
Note 3 to entry: For a normal distribution, the length of the reference interval can be expressed in terms of six
standard deviations, 6σ, or 6S, when σ is estimated from a sample.
Note 4 to entry: For a non-normal distribution, the length of the reference interval can be estimated by means of
appropriate software or probability plot (e.g. log-normal) or from the sample kurtosis and sample skewness using
the methods described in ISO/TR 22514-4.
Note 5 to entry: A quantile or fractile indicates a division of a distribution into equal units or fractions, e.g.
percentiles.
[SOURCE: ISO 3534-2:2006, 2.5.7, modified]
3.1.27
upper fraction nonconforming of the product characteristic
p
U
fraction of the distribution of the product characteristic (3.1.22) that exceeds the upper specification
limitU (3.1.12)
EXAMPLE In a normal distribution with mean μ and standard deviation σ:
UU−μ μ−
p =−1 ΦΦ=
U
σ σ
where Φ is the distribution function of the standard normal distribution.
[SOURCE: ISO 3534-2:2006, 2.5.4, modified]
6 © ISO 2014 – All rights reserved
---------------------- Page: 11 ----------------------
ISO 22514-1:2014(E)
3.1.28
lower fraction nonconforming of the product characteristic
p
L
fraction of the distribution of the product characteristic (3.1.22) that is less than the lower specification
limit L (3.1.13)
EXAMPLE In a normal distribution with mean µ and standard deviation σ:
L−μ
p =Φ
L
σ
where Φ is the distribution function of the standard normal distribution.
[SOURCE: ISO 3534-2:2006, 2.5.5, modified]
3.1.29
fraction nonconforming of the product characteristic
p
t
sum of upper fraction nonconforming of the product characteristic (3.1.27) and lower fraction nonc
...
NORME ISO
INTERNATIONALE 22514-1
Deuxième édition
2014-06-01
Méthodes statistiques dans la
gestion de processus — Aptitude et
performance —
Partie 1:
Principes et concepts généraux
Statistical methods in process management — Capability and
performance —
Part 1: General principles and concepts
Numéro de référence
ISO 22514-1:2014(F)
©
ISO 2014
---------------------- Page: 1 ----------------------
ISO 22514-1:2014(F)
DOCUMENT PROTÉGÉ PAR COPYRIGHT
© ISO 2014
Droits de reproduction réservés. Sauf indication contraire, aucune partie de cette publication ne peut être reproduite ni utilisée
sous quelque forme que ce soit et par aucun procédé, électronique ou mécanique, y compris la photocopie, l’affichage sur
l’internet ou sur un Intranet, sans autorisation écrite préalable. Les demandes d’autorisation peuvent être adressées à l’ISO à
l’adresse ci-après ou au comité membre de l’ISO dans le pays du demandeur.
ISO copyright office
Case postale 56 • CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Publié en Suisse
ii © ISO 2014 – Tous droits réservés
---------------------- Page: 2 ----------------------
ISO 22514-1:2014(F)
Sommaire Page
Avant-propos .iv
Introduction .v
1 Domaine d’application . 1
2 Références normatives . 1
3 Termes et définitions . 1
3.1 Termes fondamentaux . 2
3.2 Performance, mesures et indices . 7
3.3 Aptitude, mesures et indices .10
4 Symboles et termes abrégés .13
5 Conditions préalables à l’application .14
5.1 Aspects relatifs à la détermination des spécifications .14
5.2 Distribution et effectif d’échantillons .14
5.3 Équipements utilisés dans les études .14
5.4 Circonstances particulières .14
6 Collecte des données .15
6.1 Traçabilité des données .15
6.2 Incertitude de mesure .15
6.3 Enregistrement des données .15
6.4 Valeurs aberrantes .15
7 Analyse de la performance, de l’aptitude et du processus .16
7.1 Six types différents de performance et d’aptitude .16
7.2 Éléments de base pris en considération .16
7.3 Performance de la machine .18
7.4 Performance du processus et aptitude du processus .19
7.5 Performance de position .19
7.6 Aptitude du processus de mesure .20
7.7 Indices de performance et d’aptitude .21
8 Résultats de l’utilisation des indices .21
9 Avantages de l’utilisation des indices .22
10 Limites d’utilisation .22
Bibliographie .23
© ISO 2014 – Tous droits réservés iii
---------------------- Page: 3 ----------------------
ISO 22514-1:2014(F)
Avant-propos
L’ISO (Organisation internationale de normalisation) est une fédération mondiale d’organismes
nationaux de normalisation (comités membres de l’ISO). L’élaboration des Normes internationales est
en général confiée aux comités techniques de l’ISO. Chaque comité membre intéressé par une étude
a le droit de faire partie du comité technique créé à cet effet. Les organisations internationales,
gouvernementales et non gouvernementales, en liaison avec l’ISO participent également aux travaux.
L’ISO collabore étroitement avec la Commission électrotechnique internationale (IEC) en ce qui concerne
la normalisation électrotechnique.
Les procédures utilisées pour élaborer le présent document et celles destinées à sa mise à jour sont
décrites dans les Directives ISO/IEC, Partie 1. Il convient en particulier de prendre note des différents
critères d’approbation requis pour les différents types de documents ISO. Le présent document a été
rédigé conformément aux règles de rédaction données dans les Directives ISO/IEC, Partie 2 (voir www.
iso.org/directives).
L’attention est appelée sur le fait que certains des éléments du présent document peuvent faire l’objet de
droits de propriété intellectuelle ou de droits analogues. L’ISO ne saurait être tenue pour responsable
de ne pas avoir identifié de tels droits de propriété et averti de leur existence. Les détails concernant les
références aux droits de propriété intellectuelle ou autres droits analogues identifiés lors de l’élaboration
du document sont indiqués dans l’Introduction et/ou sur la liste des déclarations de brevets reçues par
l’ISO (voir www.iso.org/brevets).
Les appellations commerciales éventuellement mentionnées dans le présent document sont données
pour information, par souci de commodité, à l’intention des utilisateurs et ne sauraient constituer un
engagement.
Pour une explication de la signification des termes et expressions spécifiques de l’ISO liés à l’évaluation de
la conformité, ou pour toute information au sujet de l’adhésion de l’ISO aux principes de l’OMC concernant
les obstacles techniques au commerce (OTC), voir le lien suivant: Avant-propos — Informations
supplémentaires.
Le comité chargé de l’élaboration du présent document est l’ISO/TC 69, Application des méthodes
statistiques, sous-comité SC 4, Application de méthodes statistiques au management de processus.
Cette deuxième édition annule et remplace la première édition (ISO 22514-1:2009), qui a fait l’objet d’une
révision technique.
L’ISO 22514 comprend les parties suivantes, présentées sous le titre général Méthodes statistiques dans
la gestion de processus — Aptitude et performance:
— Partie 1: Principes et concepts généraux
— Partie 2: Aptitude de processus et performance des modèles de processus dépendants du temps
— Partie 3: Études de performance de machines pour des données mesurées sur des parties discrètes
— Partie 4: Estimations de l’aptitude de processus et mesures de performance
— Partie 6: Statistiques de capabilité pour un processus caractérisé par une distribution normale
multivariée
— Partie 7: Aptitude des processus de mesure
— Partie 8: Aptitude machine d’un procédé de production multimodal
Une partie supplémentaire, traitant des statistiques d’aptitude d’un processus pour les caractéristiques
d’attribut est prévue.
iv © ISO 2014 – Tous droits réservés
---------------------- Page: 4 ----------------------
ISO 22514-1:2014(F)
Introduction
La présente introduction générale au concept de l’aptitude traite de l’aptitude et de la performance de
manière générale. La consultation des ISO 22514-2, ISO 22514-3, et ISO/TR 22514-4 se révèlerait utile
pour appréhender pleinement ces concepts. Ces documents étendent le présent exposé introductif à des
utilisations plus spécifiques des procédures.
Un processus peut être discontinu ou continu. Un processus discontinu génère une séquence d’individus
différenciables tandis qu’un processus continu génère un produit continu (par exemple une bobine de
papier).
Un processus a pour objet de fabriquer un produit ou d’exécuter un service qui satisfait à un ensemble
de spécifications préétablies. Les spécifications relatives au processus étudié sont définies pour une
ou plusieurs caractéristiques du produit ou du service. Les performances ou l’aptitude d’un processus
ne tiennent toutefois compte que d’une seule caractéristique à la fois. Cette caractéristique peut être
mesurable ou dénombrable ou peut constituer une propriété. Le processus génère ainsi un processus
stochastique discontinu ou continu. Le processus discontinu peut être un processus de nombres réels,
un processus de nombres naturels ou un processus qui indique l’occurrence d’un événement donné issu
d’un ensemble d’événements pour les individus. À titre d’exemple, l’ensemble d’événements pour les
individus pourrait être du type {de couleur acceptable, de couleur non acceptable}.
En général, la notation applicable à un processus stochastique discontinu est {X }, où X est le résultat de
i i
l’élément n°i dans le processus. Dans le cas où la caractéristique est une propriété X , il s’agit d’une valeur
i
attribuée à chacun des événements de l’ensemble d’événements qui sert à caractériser le processus Pour
un processus discontinu, l’indice i est normalement le numéro de l’individu dans la séquence d’individus
générée. Cependant, il peut parfois se révéler plus approprié d’utiliser comme indice le temps par rapport
à un point fixe. Lorsque le processus est continu, il existe un grand nombre de possibilités pour l’indice
selon la nature du produit. Lorsque le produit est, par exemple, une bobine de papier, l’indice pourrait
être la longueur effective par rapport à un point de départ ou il pourrait être le temps par rapport à un
point fixe.
Il convient de noter qu’un processus stochastique comporte normalement une corrélation propre.
Un processus stochastique est stationnaire ou non stationnaire. Le présent document ne donne pas une
définition rigoureuse d’un processus stochastique stationnaire. Toutefois, un processus stationnaire
comporte une répartition de X qui est indépendante de i.
i
Les processus stochastiques qui satisfont aux spécifications sont soit des processus stationnaires, soit
des processus non stationnaires bien définis (par exemple des processus périodiques).
L’évaluation d’un processus requiert une étude de la performance. Une étude de la performance débute
en fait comme une étude théorique de tous les éléments contenus dans le processus avant la mise en
œuvre physique dudit processus. Lorsque les paramètres des différentes phases du processus ont été
analysés et redéfinis, le processus est mis en œuvre (peut-être uniquement comme un processus d’essai).
L’échantillonnage du processus mis en œuvre constitue la base d’initiation de la partie numérique
de l’étude de la performance. Il s’agira de répondre correctement à un certain nombre de questions
concernant le processus, et ce, au-delà de tout doute raisonnable. La question la plus importante à
laquelle il doit être répondu consiste à déterminer si le processus est un processus stationnaire stable
ou prévisible pendant une période raisonnable. Il est alors important pour le processus d’identifier sa
loi de probabilité et d’obtenir des estimations des paramètres de répartition avec une variance faible
raisonnable. Sur la base de ces informations, la phase suivante de l’étude de la performance consisterait
à représenter les propriétés des caractéristiques examinées et à déterminer si elles sont acceptables.
Si les propriétés ne peuvent pas être acceptées, les paramètres du processus proprement dit seront
modifiés de manière à obtenir un processus ayant des propriétés acceptables.
Considérons, dans un premier temps, un processus bien défini et mis en œuvre qui a été accepté au
moyen d’une étude de la performance. La phase suivante du processus consisterait alors à s’assurer
© ISO 2014 – Tous droits réservés v
---------------------- Page: 5 ----------------------
ISO 22514-1:2014(F)
que les paramètres du processus et, ainsi, du processus stochastique, ne changent pas, ou changent de
manière prévisible. Pour ce faire, il y a lieu de définir une étude d’aptitude appropriée.
Les études en question portant sur les indices de performance et d’aptitude sont aujourd’hui de plus en
plus utilisées pour évaluer le matériel de production, un processus, voire un équipement de mesure, par
rapport aux critères de spécification. Différents types d’études sont utilisés selon les circonstances.
vi © ISO 2014 – Tous droits réservés
---------------------- Page: 6 ----------------------
NORME INTERNATIONALE ISO 22514-1:2014(F)
Méthodes statistiques dans la gestion de processus —
Aptitude et performance —
Partie 1:
Principes et concepts généraux
1 Domaine d’application
La présente partie de l’ISO 22514 décrit les principes fondamentaux de l’aptitude et de la performance
des processus de fabrication. Elle a été élaborée pour fournir des recommandations concernant les
circonstances dans lesquelles une étude d’aptitude est exigée ou nécessaire pour déterminer si le résultat
d’un processus de fabrication ou le matériel de production (une machine de fabrication) est acceptable
selon des critères appropriés. Ces circonstances sont courantes dans le processus de contrôle de la
qualité, lorsque l’objet de l’étude fait partie intégrante d’un certain type d’acceptation de la production.
Ces études peuvent également être utilisées lorsqu’un diagnostic est requis concernant le rendement
d’une production ou comme partie intégrante d’une démarche de résolution de problèmes. Les méthodes
utilisées, très polyvalentes, ont été appliquées dans de nombreuses situations.
La présente partie de l’ISO 22514 est applicable:
— aux organismes qui cherchent à s’assurer que les exigences relatives aux caractéristiques de leurs
produits sont satisfaites;
— aux organismes qui cherchent à s’assurer que leurs fournisseurs satisfont et satisferont aux
spécifications de leurs produits;
— à ceux, en interne ou à l’extérieur de l’organisme, qui auditent ce dernier en termes de conformité
aux exigences relatives au produit;
— à ceux, à l’intérieur de l’organisme, qui analysent et évaluent la situation de production existante
pour identifier les secteurs d’amélioration du processus.
2 Références normatives
Les documents ci-après, dans leur intégralité ou non, sont des références normatives indispensables à
l’application du présent document. Pour les références datées, seule l’édition citée s’applique. Pour les
références non datées, la dernière édition du document de référence s’applique (y compris les éventuels
amendements).
ISO 1101, Spécification géométrique des produits (GPS) — Tolérancement géométrique — Tolérancement
de forme, orientation, position et battement
ISO 22514-7, Méthodes statistiques dans la gestion de processus — Aptitude et performance —
Partie 7: Aptitude des processus de mesure
3 Termes et définitions
Pour les besoins du présent document, les termes et définitions suivants s’appliquent.
© ISO 2014 – Tous droits réservés 1
---------------------- Page: 7 ----------------------
ISO 22514-1:2014(F)
3.1 Termes fondamentaux
3.1.1
exigence
besoin ou attente formulé(e), habituellement implicite, ou imposé(e)
[SOURCE: ISO 9000:2005, 3.1.2]
3.1.2
processus
ensemble d’activités corrélées ou interactives qui transforme des éléments d’entrée en éléments de
sortie
Note 1 à l’article: Les éléments d’entrée d’un processus sont généralement les éléments de sortie d’autres processus.
Note 2 à l’article: Les processus d’un organisme sont généralement planifiés et mis en œuvre dans des conditions
maîtrisées afin d’apporter une valeur ajoutée.
[SOURCE: ISO 3534-2:2006, 2.1.1, modifiée]
3.1.3
système
ensemble d’éléments corrélés ou interactifs
[SOURCE: ISO 9000:2005, 3.2.1]
3.1.4
produit
résultat d’un processus
Note 1 à l’article: Quatre catégories génériques de produits sont:
— les services (par exemple, transport);
— les logiciels (par exemple, programme informatique);
— les matériels (par exemple, pièces mécaniques de moteur); et
— les produits issus de processus à caractère continu (par exemple, lubrifiant).
De nombreux produits sont constitués d’éléments appartenant à différentes catégories génériques de produits. La
qualification du produit dépend de l’élément dominant.
Note 2 à l’article: En mathématique, le concept de produit est limité au résultat de la multiplication.
[SOURCE: ISO 3534-2:2006, 1.2.32]
3.1.5
caractéristique
trait distinctif (d’un individu)
[SOURCE: ISO 9000:2005, 3.5.1, modifiée]
Note 1 à l’article: Le terme «individu» est défini dans l’ISO 3534-2:2006, définition 1.2.11.
3.1.6
qualité
aptitude d’un ensemble de caractéristiques (3.1.5) intrinsèques d’un produit (3.1.4) à satisfaire les
exigences (3.1.1) des clients et des autres parties intéressées
Note 1 à l’article: Dans l’ISO 9000:2005, 3.1.1, la définition du terme «qualité» ne précise pas qui définit les
exigences.
2 © ISO 2014 – Tous droits réservés
---------------------- Page: 8 ----------------------
ISO 22514-1:2014(F)
3.1.7
caractéristique de produit
caractéristique (3.1.5) intrinsèque d’un produit (3.1.2)
Note 1 à l’article: Les caractéristiques de produit peuvent être quantitatives ou qualitatives.
Note 2 à l’article: La caractéristique de produit peut être multidimensionnelle.
3.1.8
caractéristique de processus
caractéristique (3.1.5) intrinsèque d’un processus (3.1.4)
Note 1 à l’article: Les caractéristiques de processus peuvent être quantitatives ou qualitatives.
Note 2 à l’article: La caractéristique de processus peut être multidimensionnelle.
3.1.9
caractéristique qualité
caractéristique (3.1.5) intrinsèque d’un produit (3.1.4), d’un processus (3.1.2), ou d’un système (3.1.3)
relative à une exigence (3.1.1)
Note 1 à l’article: Les caractéristiques qualité peuvent être quantitatives ou qualitatives.
Note 2 à l’article: La caractéristique qualité peut être multidimensionnelle.
Note 3 à l’article: Souvent, il existe une corrélation forte entre une caractéristique de processus et une
caractéristique de produit, effective du fait du processus. En principe, toutefois, l’exigence individuelle relative
à la caractéristique de processus et celle relative à la caractéristique de produit sont différentes. Chacune de
ces deux exigences individuelles fait partie intégrante de l’exigence qualité relative au processus, ainsi que de
l’exigence qualité relative au produit, respectivement.
3.1.10
spécification
document formulant des exigences (3.1.1)
Note 1 à l’article: Une spécification peut être liée à des activités (par exemple document de procédure, spécification
de processus et spécification d’essai), ou à des produits (3.1.4) (par exemple spécification de produit, spécification
de performance et plan).
[SOURCE: ISO 9000:2005, 3.7.3]
3.1.11
limite de spécification
valeur limite spécifiée pour une caractéristique (3.1.5)
[SOURCE: ISO 3534-2:2006, 3.1.3]
Note 1 à l’article: Parfois, les limites de spécification sont appelées «limites de tolérance».
3.1.12
limite de spécification supérieure
U
limite de spécification (3.1.11) qui définit la valeur la plus élevée pouvant être attribuée à une
caractéristique qualité et pouvant par ailleurs être considérée conforme
Note 1 à l’article: U est le symbole préférentiel pour la limite de spécification supérieure.
[SOURCE: ISO 3534-2:2006, 3.1.4, modifiée]
© ISO 2014 – Tous droits réservés 3
---------------------- Page: 9 ----------------------
ISO 22514-1:2014(F)
3.1.13
limite de spécification inférieure
L
limite de spécification (3.1.11) qui définit la valeur la moins élevée pouvant être attribuée à une
caractéristique qualité et pouvant par ailleurs être considérée conforme
Note 1 à l’article: L est le symbole préférentiel pour la limite de spécification inférieure.
[SOURCE: ISO 3534-2:2006, 3.1.5, modifiée]
3.1.14
intervalle de spécification
intervalle de tolérance
zone de tolérance
intervalle entre les limites de spécification (3.1.11) supérieure et inférieure
Note 1 à l’article: Ce terme est complètement différent d’un intervalle de tolérance statistique, qui est un intervalle
comportant des limites stochastiques.
3.1.15
valeur cible
T
valeur désirée ou de référence d’une caractéristique (3.1.5) définie dans une spécification (3.1.10)
[SOURCE: ISO 3534-2:2006, 3.1.2]
3.1.16
valeur nominale
valeur de référence d’une caractéristique (3.1.5) indiquée dans une spécification
Note 1 à l’article: Dans l’ISO 3534-2, la valeur nominale et la valeur cible sont synonymes, avec la valeur cible
comme terme retenu. Il est nécessaire de distinguer la valeur de référence définie dans une spécification et la
valeur retenue utilisée en production.
3.1.17
valeur réelle
valeur d’une grandeur dans une caractéristique (3.1.5)
3.1.18
variation
différence entre les valeurs d’une caractéristique (3.1.5)
Note 1 à l’article: La variation est souvent exprimée comme une variance ou un écart-type.
[SOURCE: ISO 3534-2:2006, 2.2.1]
3.1.19
cause aléatoire
cause commune
cause fortuite
source de variation du processus (3.1.18) intrinsèque à un processus (3.1.2)
dans le temps
Note 1 à l’article: Dans un processus soumis uniquement à une variation de cause aléatoire, la variation est
prévisible dans les limites statistiquement établies.
Note 2 à l’article: La réduction de ces causes donne lieu à l’amélioration du processus. Cependant, l’effort lié à
leur identification, leur réduction, voire leur élimination fera l’objet d’une analyse coût/bénéfice en termes de
résolubilité technique et d’économie.
[SOURCE: ISO 3534-2:2006, 2.2.5]
4 © ISO 2014 – Tous droits réservés
---------------------- Page: 10 ----------------------
ISO 22514-1:2014(F)
3.1.20
caractéristique de produit maîtrisée
paramètre de caractéristique de produit (3.1.7) de la distribution des valeurs de caractéristique qui ne
changent pratiquement pas ou qui changent uniquement de manière connue ou dans des limites connues
3.1.21
processus stable
processus en état de maîtrise statistique
processus (3.1.2) uniquement soumis à des causes aléatoires (3.1.19)
Note 1 à l’article: Une production maîtrisée est une production dont les processus sont maîtrisés.
Note 2 à l’article: Un processus stable se comporte généralement comme si les échantillons issus du processus
étaient, à tout moment, de simples échantillons aléatoires issus de la même population.
Note 3 à l’article: Cet état n’implique pas que la variation aléatoire est grande ou petite, s’inscrivant ou ne s’inscrivant
pas dans la spécification, mais indique que la variation est prévisible au moyen de techniques statistiques.
[SOURCE: ISO 3534-2:2006, 2.2.7, modifiée]
3.1.22
distribution d’une caractéristique de produit
information sur le comportement probabiliste d’une caractéristique de produit (3.1.7)
Note 1 à l’article: La distribution contient l’information numérique concernant la caractéristique de produit, à
l’exception de l’ordre dans lequel les individus ont été produits.
Note 2 à l’article: La distribution de la caractéristique de produit existe, que la caractéristique de produit soit
ou non enregistrée. Cette distribution dépend de conditions techniques telles que les lots d’entrée, les outils, les
opérateurs, etc.
Note 3 à l’article: Des données doivent être collectées si l’on souhaite obtenir des informations sur la distribution
de la caractéristique de produit. La distribution observée dépend, en outre, des conditions techniques (voir
Note 2), ainsi que des conditions suivantes afférentes à la collecte des données:
— le mesurage;
— l’intervalle de temps pendant lequel l’échantillonnage a lieu;
— la fréquence d’échantillonnage.
Les conditions techniques (voir Note 2) et les conditions de collecte des données doivent toujours être spécifiées.
Note 4 à l’article: La distribution de la caractéristique de produit peut être représentée selon l’une des voies de
représentation des distributions et des données issues de ces distributions. L’histogramme est utilisé fréquemment
pour les données issues d’une distribution, tandis que la fonction de densité est utilisée fréquemment pour un
modèle de distribution de la caractéristique de produit.
Note 5 à l’article: Dans les paragraphes suivants, la distribution de la caractéristique de produit sera examinée
dans des conditions différentes mais bien définies, telles que la performance et l’aptitude, où la performance est
la valeur la moins restrictive.
3.1.23
classe de distributions
famille particulière de distributions (3.1.22), dont chacun des membres a les mêmes attributs communs
par lesquels la famille est entièrement spécifiée
EXEMPLE 1 La classe des distributions normales, où la moyenne et l’écart-type représentent les paramètres
inconnus. Il est souvent fait référence à la classe des distributions normales simplement en tant que loi normale.
EXEMPLE 2 Loi de Weibull à plusieurs formes et trois paramètres, avec paramètres, valeur centrale, forme et
échelle.
EXEMPLE 3 Les distributions continues unimodales.
© ISO 2014 – Tous droits réservés 5
---------------------- Page: 11 ----------------------
ISO 22514-1:2014(F)
Note 1 à l’article: La classe de la distribution peut souvent être entièrement spécifiée par les valeurs des paramètres
appropriés.
[SOURCE: ISO 3534-2:2006, 2.5.2, modifiée]
3.1.24
modèle de distribution de la caractéristique de produit
distribution spécifiée (3.1.22) ou classe de distributions (3.1.23)
EXEMPLE 1 Un modèle de distribution pour une caractéristique de produit telle que le diamètre d’un boulon
peut être la loi normale avec une moyenne de 15 mm et un écart-type de 0,05 mm. Il s’agit d’un modèle totalement
spécifié.
EXEMPLE 2 Un modèle applicable à la même situation que dans l’Exemple 1 peut être la classe de distributions
normales, sans spécification d’une distribution particulière. Il s’agit d’un modèle à classe de distributions
normales.
[SOURCE: ISO 3534-2:2006, 2.5.3]
3.1.25
limites de référence de la caractéristique de produit
X , X
0,135 % 99,865 %
fractile de la distribution de la caractéristique de produit (3.1.22)
EXEMPLE Si la distribution de la caractéristique de produit est normale avec une moyenne μ et un écart-type
σ, les limites sont μ ± 3σ, si les fractiles 0,135 % et 99,865 % traditionnels sont utilisés.
Note 1 à l’article: Les conditions de la distribution de la caractéristique de produit doivent être spécifiées, voir
Note 2 et Note 3 du paragraphe 3.1.22.
Note 2 à l’article: Les fractiles 0,135 % et 99,865 % sont traditionnellement utilisés.
3.1.26
intervalle de référence d’une caractéristique de produit
intervalle compris entre le fractile de distri
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.