MEASUREMENT SYSTEMS ANALYSIS Reference Manual Fourth Edition First Eden, October 1990 » Second Eelion, February 1995; Sacond Printing, June 1988 Third Galton, March 2002; Second Printing May 2003; Fourth Ealion June 2010, Copyiight © 1990 © 1995 © 2002, ©2070 Chrysler Group LLC Ford Motor Company General Motors Corporation ISBN 978-1-60-594211-5FOREWORD This Reference Manual was developed by a Measurement Systems Analysis (MSA) Work Group, sanctioned by the Chrysler Group LLC, Ford Motor Company, and Genetal Motors Corporation Supplier Quality Requirements Task Force, and under the auspices of the Automotive Industry Action Group (AIAG) The Work Group responsible for this Fourth Edition were Michael Down (General Motors Corporation), Frederick Czubak (Chrysler Group LLC), Gregory Gruska (Omnex), Steve Stabley (Cummins, Inc ) and David Benham, The manual is an introduction to measurement system analysis. It is not intended to limit evolution of analysis methods suited to particular processes or commodities. While these guidelines are intended to cover normally occusring measurement system situations, there will be questions that arise. These questions should be directed to your authorized customer representative This Manual is copyrighted by Chiysler Group LLC, Ford Motor Company, and General Motors Corporation, with all rights reserved, 2010 Additional manuals can be ordered from AIAG at www.aiag.org. Permission to reproduce portions of this manual for use within supplier organizations may be obtained from AIAG at www.aiag.org June 2010MSA 4" Edition Quick Guide Range, Average & Range, ANOVA, in Basie Variable ‘Bias, Linearity, Contol Charts Basic Aunts seen ipa ironcanh Altemate Approaches Iv coer Bias Linearity Control Charts Multiple Systems, Gages eae 7 pad pte Control Charts ANOVA Regression Analysis 10,1V Miscellaneous Alemate Approaches Vv | oie White Papers ~ available at AIAG website (wow aiag org) NOTE: Regarding the use of the GRR standard deviation Historically, by convention, a 99% spread has been used to represent the “full” spread of measurement error, represented by a 5.15 multiplying factor (where Oy» is multiplied by 5.15 to represent a total spread of 99%) A99.73% spread is represented by a multiplier of 6.0, which is 43 and represents the full spread of a “normal” curve If the reader chooses to increase the coverage level, or spread, of the total measurement variation to 99.73%, use 6.0 as a multiplier in place of 5 15 in the calculations Note: The approach used in the 4" Edition is to compare standard deviations. This is equivalent to using the multiplier of 6 in the historical approach. Awareness of which multiplying factor is used is crucial to the integrity of the equations and resultant calculations. This is especially important if a comparison is to be made between measurement system variability and the tolerance. Consequently, if an approach other than that described in this manual is used, a statement of such must be stated clearly in any results or summaries (particularly those provided to the customer)TABLE OF CONTENTS MSA s* Edition Quick Guide ee eee TABLE OF CONTENTS 0.0.00 aes “ List of Tables. : aan List of Figures. ae CHAPTER General Measarement System Guidelines a ‘Section A Introduction, Purpose and Terminology Intodvetion Purpose Teiminology . Section B The Measurement Process Measurement Systems The Effects of Measurement System Vatability Section C Measurement Seategy and Planing Section D Measurement Source Development Gage Source Selection Process. Section F Measurement Isses ‘Section F Measurement Uncertainty. Section G Measurement Problem Analysis CHAPTER TI General Concepts for Assessing Measurement Systems. actu Section A Bacegrownd Section B SclectingDeveloping Test Procedures Seotion C Preparation fora Measurement System Study Section D Analysis ofthe Reslts CHAPTER IIL Recommended Practices for Replicable Measurement Systems. . Section A Example Test Procedures Section B Variable Meesurement System Study Guidelines Guidelines for Determining Sabilty Guidelines for Determining Bias — Independent Sample Method Guidelines for Determining Bias ~ Contol Chat Method Guideines for Determining Linearity Guidelines for Determining Repeatbilty and Reproducibility Range Method. Average and Range Method Analysis of Variance (ANOVA) Method Section € Attribute Measarement Systems Study Risk Analysis Methods Signal Detection Approach ‘Analytic Method CHAPTER IV Other Measurement Concepts and Practices ~ ‘Section A Practices for Non- Replicable Measurement Systems. Destructive measurement systems Systems where the part changes on weltest Section B Stability Studies Section C Variability Studies. Section D Recognizing the Etfect of Excessive Within-Pat Variation Section F Average and Range Method ~ Additional Treatment Section F Gage Performance Curve Section G Reducing Variation Throvgh Mutiple Readings Section F Pooled Standard Deviation Approach to GRR APPENDICES 101 102 103 123 131 BL 143 145 ASI 133 133 153 155 tel 167 169 7 133 185 193195 Appendix B. POE Re cieti cone 99 Impact of GRR on the Capability Index Cp 199 Formulas: 199 Analysis: 199 Graphical Analysis 201 APPendIX Coonan none nein Pat : at 203 Appendix D.... ee monn nnnne 20S Gage R Study 205 Appendix E...-.. ae eee ae 207 “Alternate P Calculation sing Enor Correction Term 207 ADDENEIX Foo nsemnremns sn nnnnncnens ee eee eae PISMOEA Error Model 209 GIOS841F oe ae ease eee eaiat Reference List ~... te es inne BAD Sample Forms. as . eS 223 227 Index viTable 1-81: List of Tables Control Philosophy and Driving Interest Table II-D 1: GRR Criteria Table II-B 1: Bias Study Data Table IlI-B 2: Bias Study ~ Analysis of Bias Study Table III-B 3: Bias Study ~ Analysis of Stability Study for Bias Table Il-B 4: Linearity Study Data Table III-B 5: Linearity Study ~ Intermediate Results Table III-B 6: Gage Study (Range Method) Table III-B 6a: Gage Repeatability and Reproducibilty Data Collection Sheet Table III-B 7: ANOVA Table Table II-B 8: ANOVA Analysis % Variation & Contribution Table III-B 9: Comparison of ANOVA and Average and Range Methods Table II-B 10: GRR ANOVA Method Report Table Iil-C 1: Attribute Study Data Set. : Table IIl-C 2: Cross tabulation Study Results, Table III-C 3: Kappa Summary Table IC -4: Comparisons of Appraisers to Reference Table III-C 5: Study Effectiveness Table Table III-C 6: Example Effectiveness Criteria Guidelines Table III-C 7: Study Effectiveness Summary Table ll:C 8: Table IILC 1 sorted by Ref Value Table IV-A 1: Methods Based on Type of Measurement System Table IV-H 1: Pooled Standard Deviation Analysis Data Set Table At Table A 2: Table A 3: Table A 4: Table A 5: Table B 1: Table C 1 Table F 1 Estimate of Variance Components 6 Sigma Spread Analysis of Variance (ANOVA) Tabulated ANOVA Results Tabulated ANOVA Results Comparison of Obsarved to Actual Cp Table Examples of the PISMOEA Model vii 140 140 143, 189 195 196 197 198 198 204 203 244List of Figures Figure LA 1: Example of a Traceability Chain for a Length Measurement Figure 8 1: Measurement System Variability Cause and Effect Diagram Figure LE 2: Discrimination Figure I-E 3: Impact of Number of Distinct Categories (nde) of the Process Distribution on Control and Analysis Activities... Figure HE 4: Process Control Charts Figure HE 5: Characteristics of the Measurement Process Variation Figure IE 6: Relationships between Bias and Repeatability Figure tNI-8 4: Control Chart Analysis for Stability Figure IIIB 2: Bias Study ~ Histogram of Bias Study Figure IIB 3: Linearity Study — Graphical Analysis Figure NB 4: Average Chart — "Stacked Figure III-B 5: Average Chart — “Unstacked Figure II-B 6: Range Chart ~ “Stacked” Figure III 7: Range Chart ~ “Unstacked” Figure !I-8 8: Run Chart by Part Figure IIIB 9: Scatter Plot, Figure lil-8 10: Whiskers Chart Figure III-B 14: Error Charts... Figure !I-8 12: Normalized Histogram, Figure III 13: X-Y Plot of Averages by Size Figure Ill-B 14: Comparison X-Y Plots Figure III-B 18: Completed GR&R Data Collection Sheet Figure Ii8 16: Gage Repeatability and Reproducibility Report Figure Ili-B 18: Residual Pot Figure IIl-C 1: Example Process with Pp = Ppk = 0.50. Figure llI-C 2: The “Gray” Areas Associated with the Measurement System Figure Ili-C 3: Example Process with Pp = Ppk = 1.33. Figure ILC 4: Attribute Gage Performance Curve Plotted on Normal Probability Paper Figure lll-C 5. Attribute Gage Performance Curve Figure IV-E 1; Measurement Evaluation Control Chart (X & R)-1 Figure IV-E 2: Measurement Evaluation Control Chart (X & R)-2 Figure IV-E 3: Alternate Computations for Evaluating a Measurement Process (Part 1 of 2) Figure IV-E 4: Alternate Computations for Evaluating a Measurement Process (Part 2 of 2) Figure IV-F 1: Gage Performance Curve Without Error Figure IV-F 2: Gage Performance Curve Example Figure IV-F 3: Gage Performance Curve Plotted on Normal Probability Paper Figure IV-H 1: Pooled Standard Deviation Study Graphical Analysis Figure IV-H 2: Dot diagram of h values. Figure IV-H 3: Dot diagram of k values Figure B 1: Observed vs. Actual Cp (process based). Figure B 2; Observed vs. Actual Cp (tolerance based) 114 132 141 149 150 472 173 174 175 180 181 182 188 191 192 201 202General Measurernent System Gi CHAPTER I General Measurement System GuidelinesChapter I~ Section A Introduction, Purpose and TerminologySection A Introduction, Purpose and Terminology Introduction, Purpose and Terminology Introduction Quality of Measurement Data Measurement data are used more often and in more ways than ever before For instance, the decision to adjust 2 manufacturing process is now commonly based on measurement data The data, or some statistic calculated fiom them, are compared with statistical control limits for the process, and if the comparison indicates that the process is out of statistical control, then an adjustment of some kind is made Otherwise, the process is allowed to run without adjustment. Another use of measurement data is to determine if a significant relationship exists between two or more variables. For example, it may be suspected that a critical dimension on a molded plastic partis related to the temperature of the feed material. That possible relationship could be studied by using a statistical procedure called regression analysis to compare measurements of the critical dimension with measurements of the temperature of the feed material Studies that explore such relationships are examples of what Di. W. 5. Deming called analytic studies. In general, an analytic study is one that increases knowledge about the system of causes that affect the process Analytic studies are among the most important uses of measurement data because they lead ultimately to better understanding of processes. The benefit of using a data-based procedure is largely determined by the quality of the measurement data used. If the data quality is tow, the benefit of the procedure is likely to be low. Similarly, if the quality of the data is high, the benefit is likely to be high also. To ensure that the benefit derived from using measurement data is great enough to warrant the cast of obtaining it, attention needs to be focused on the quality of the data The quality of measurement data is defined by the statistical properties of multiple measurements obtained fiom a measurement system operating undet stable conditions. For instance, suppose that a measurement system, operating under stable conditions, is used to obtain several measurements of a certain characteristic If the measurements are all “close” to the master value for the characteristic, then the quality of the data is said to be “high” Similarly, if some, or all, of the measurements are “far away” from the master value, then the quality of the data is said to be “low” The statistical properties most commonly used to characterize the quality of data are the bias and variance of the measurement system, The property called bias refers to the location of the data relative to a reference (master) value, and the property called variance refers to the spread of the data One of the most common reasons for low-quality data is too much variation. Much of the variation in a set of measurements may be due to the interaction between the measurement system and its environment For instance, @‘Chapter I Section A Introduction, Purpose and Terminology Purpose Terminology measurement system used to measure the volume of liquid in a tank may be sensitive to the ambient temperature of the enviroment in which it is used. In that case, variation in the data may be due either to changes in the volume or to changes in the ambient temperature That makes interpreting the data more difficult and the measurement system, therefore, less desirable If the interaction generates too much variation, then the quality of the data may be so low that the data are not useful For example, a measurement system with @ large amount of variation may not be appropriate for use in analyzing a manufacturing process because the measurement system’s variation may mask the variation in the manufacturing process Much of the work of managing 2 measurement system is directed at monitoring and controlling variation. Among other things, this means that emphasis needs to be placed on learning how the measurement system interacts with its environment so that only data of acceptable quality are generated The purpose of this document is to present guidelines for assessing the quality of a measurement system Although the guidelines are general enough to be used for any measurement system, they are intended primarily for the measurement systems used in the industrial world, This document is not intended to be a compendium of analyses for all measurement systems its primary focus is measurement systems where the readings can be replicated on each part Many of the analyses are useful with other types of measurement systems and the manual does contain 1eferences and suggestions. It is recommended that competent statistical resources be consulted for more complex or unusual situations not discussed here Customer approval is required for measurement systems analysis methods not covered in this manual ‘The discussion of the analysis of measurement system can become confusing and misleading without an established set of terms to refer to the common statistical properties and related elements of the measurement system. This, section provides a summary of such terms which are used in this manuat In this document, the following terms are used: ‘¢ Measurement is defined as “the assignment of numbers [or values} to material things to represent the relations among them with respect to particular propetties” This definition was first given by C Eisenhart (1963) The process of assigning the numbers is defined as the measurement process, and the value assigned is defined as the measurement value.a Intoduction, Purpose and Terminology © Gage is any device used to obtain measurements; frequently used to refer specifically to the devices used on the shop floor; includes goino-go devices (also, see Reference List: ASTM F456-96) © Measurement System is the collection of instruments or gages, standards, operations, methods, fixtures, software, personnel, environment and assumptions used to quantify a unit of measure ot fix assessment to the feature characteristic being measured; the complete process used to obtain measurements From these definitions it follows that a measurement process may be viewed as @ manufacturing process that produces numbers (data) for its output ‘Viewing a measurement system this way is useful because it allows us to bring to bear all the concepts, philosophy, and tools that have already demonstrated their usefulness in the area of statistical process control Summary of Terms! Standard © Accepted basis for comparison ‘+ Citeria for acceptance * Known value, within stated limits of uncertainty, accepted as a true value * Reference value A standard should be an operational definition: a definition which wt yield the same results when applied by the supplier or customer, with the same meaning yesterday, today, and tomorrow Basic equipment Sip © Discrimination, readability, resolution fe=een rvereTe! =] Y Alias: smallest readable unit, measurement resolution, scale limit, or detection limit ‘An inherent propatty fixed by design ‘Smallest scale unit of measure ot output for an instrument ‘Always teported as a unit of measure 10 to T mule of thumb KAKA © Effective resolution Y The sensitivity of a measurement system to process variation for a particular application "See Chapter I, Seetion E for terminology definitions and discussionChapter I~ Section A Introduction, Purpose and Terminology Y Smallest input that results in a usable ourput signal of measurement Y Always reported as 2 unit of measure + Reference value Y Accepted value of an artifact Y Requites an operational definition Y Used as the surrogate for the true value © True value Y Actual value of an artifact Y Unknown and unknowable Location variation cae © Accuracy r ¥ *Closeness” to the true value, or to an accepted reference value Y ASTM includes the effect of location and width esrors /\\ rege Y Difference between the observed average of measurements and the reference value ¥ A systematic error component of the measurement system VL * * Stability \ Y The change in bias over time YA stable measurement process is in statistical contiol with respeet to location Y Alias: Drift © Linearity K mo Y The change in bias over the normal operating range x JN V The correlation of multiple and independent bias errors over the eer on operating range YA systematic error component of the measurement systemIntroduction, Purpose and Terminology Width variation © Precision” ¥ “Closeness” of repeated readings to each other A random etror component of the measurement system ‘+ Repeatability a Y Variation in measurements obtained with one measuring instrument when used several times by an appraiser while ‘measuring the identical characteristic on the same part 5 ¥ The variation in successive (short-term) trials under fixed and TRepenabity defined conditions of measurement ¥ Commonly referred to as EV ~ Equipment Variation Y Instrument (gage) capability or potential ¥ Within-system vatiation ‘+ Reproducibility Y Variation in the average of the measurements made by different appraisers using the same gage when measuring a characteristic ‘on one part | oe Y For product and process qualification, error may be appraiser, environment (time), or method ¥ Commonly referred to as A'V — Appraiser Variation | ¥ Between-system (conditions) variation VY ASIM £456.96 includes repeatability, Iaboratory, and environmental effects as well as appraiser effects © GRR or Gage R&R Y Gage repeatability and reproducibility: the combined estimate of ‘measurement system repeatability and reproducibility ¥ Measurement system capability; depending on the method used, may or may not include the effects of time ‘© Measurement System Capability Y Short-term estimate of measurement system variation (eg, “GRR” including graphics) 2 I ASTM documents there is no such thing asthe precision of a measurement system; ie, the precision cannot be represented by a single number‘Chapter L~Section A Introduction, Purpose and Terminology © Measurement System Performance Long-term estimate of measurement system variation (e.g, long- term Control Chart Method) + Sensitivity Smallest input that results in a detectable output signal Y Responsiveness of the measurement system to changes in measured feature Y Determined by gage design (disctimination), inherent quality (Original Equipment Manufacturer), in-service maintenance, and ‘operating condition of the instrument and standard Y Always reported as a unit of measure a + Consisteney serge Y The degree of change of repeatability over time Y A consistent measurement process is in statistical control with 4 respect to width (variability) © Uniformity , AX JN The change in repeatability over the normal operating range a ¥ Homogeneity of repeatability System variation Measurement system variation can be characterized as: © Capability Variability in readings taken over a short period of time + Performance Variability in readings taken over a long period of time Y Based on total variation ‘+ Uncertainty Y Anestimated range of values about the measured value in which the true value is believed to be contained I characterizations of the total variation of the measurement system The measurement | assume that the system is stable and consistent. For example, the system must be stable {components of variation can include any combination of the items and consistent 4 shown in -B 1Standards and Traceability National Measurement Institutes Traceability Introduction, Purpose and Terminology The National Institute of Standards and Technology (NIST) is the principal National Measurements Institute (NMI in the United States serving under the US Department of Commerce NIST, formerly the National Bureau of Standards (NBS), serves as the highest level authority for metrology in the US. NIST’s primary responsibility is to provide measuement services and maintain measurement standards that assist U S. industry in making traceable measurements which ultimately assist in trade of products and services NIST provides these services directly to many types of industries, but primarily to those industries that requite the highest level of accuracy for theit products and that incorporate state-of-the-att measurements in their processes. Most of the industrialized countries throughout the world maintain theiz own NMIs and similar to NIST, they also provide a high level of metology standards or measurement services for their respective countries. NIST works collaboratively with these other NMTs to assure measurements made in one country do not differ fiom those made in another This is accomplished through Mutual Recognition Asrangements (MRAs) and by perfouming interlaboratory comparisons between the NMIs. One thing to note is that the capabilities of these NMIs will vary ftom country to country and not all types of measurements are compared on a regulat basis, so differences can exist This ig why it is important to understand to whom measurements are traceable and how traceable they are Traceability is an important concept in the trade of goods and services ‘Measurements that are traceable to the same or similar standards will agree more closely than those that are not traceable This helps reduce the need for re-test, rejection of good product, and acceptance of bad product Traceability is defined by the ISO International Vocabulary of Basic and General Terms in Metrology (VIM) as: “The property of a measurement or the value of a standard whereby it can be related to stated references, usually national or international standardh, through an unbroken chain of comparisons all having stated uncertainties." ‘The traceability of a measurement will typically be established through a chain of comparisons back to the NMI. However, in many instances in industry, the traceability of a measurement may be linked back to an agreed upon reference value o “consensus standard” between @ customer and a suppliet The traceability linkage of these consensus standards to the NMI may not always be clearly understood, so ultimately it is critical that the ‘measurements are traceable to the extent that satisfies customer needs. With the advancement in measurement technologies and the usage of state-of-the- art measurement systems in industry, the definition as to where and how a measurement is traceable is an ever-evolving conceptCaapter 1 seeuon A Introduction, Purpose and Terminology ‘Wavelength Standard * Interference ‘Comparator Laser Reference Gage Interferometer __Blocks/Comparator Working Standard cMM Gage Blocks { Production Gage Fixture Gage Micrometers Figure T-A 1: Example of a Traceability Chain for a Length Measurement NMIs work closely with various national labs, gage suppliers, state-of-the-art manufacturing companies, ete to assure that their reference standards are properly calibrated and directly traceable to the standards maintained by the NMI. These government and private industry organizations will then use theit standards to provide calibration and measurement services to theit customers’ metrology or gage laboratories, calibrating working ot other primary standards. This linkage or chain of events ultimately finds its way ‘onto the factory floor and then provides the basis for measurement traceability Measurements that can be connected back to NIST through this, unbroken chain of measurements are said to be traceable to NIST Not all organizations have metrology or gage laboratories within their facilities therefore depend on outside commercial/independent laboratories to | provide traceability calibration and measurement services This is an acceptable and appropriate means of attaining traceability to NIST, provided that the capability of the commercial/independent laboratory can be assured. through processes such as laboratory accreditation A calibration system is a set of operations that establish, under specified Calibration conditions, the relationship between a measuring device and a traceable Systems standard of known reference value and uncertainty Calibration may also include steps to detect, correlate, report, or eliminate by adjustment any discrepancy in accuracy of the measuring device being compared. The calibration system determines measurement traceability to the measurement systems through the use of calibration methods and standards Traceability is the chain of calibration events originating with the calibration standards of appropriate metrological capability or measurement uncertainty. Each calibration event includes all of the elements necessary including standards, measurement and test equipment being verified, calibration methods and procedures, records, and qualified personnel I 10True Value Introduction, Purpose and Terminology An organization may have an intesnal calibration laboratory ot organization which controls and maintains the elements of the calibration events These intemal laboratories will maintain a laboratory scope which lists the specitic calibrations they are capable of performing as well as the equipment and methods/procedures used to perform the calibrations The calibration system is part of an oiganization’s quality management system and therefore should be included in any internal audit requirements. Measnrement Assurance Progiams (MAPs) can be used to verify the acceptability of the measurement processes used throughout the calibration system, Generally MAPs will include verification of « measurement system’s results through a secondary independent measurement of the same feature or parameter, Independent measurements imply that the traceability of the secondary measurement process is derived from a separate chain of calibration events fiom those used for the initial measurement. MAPs may also include the use of statistical process control (SPC) to track the long-term stability of a measurement process Note: ANSIINGSL Z640.3 and ISO 10012 each provide models for many of the elemants of a calibration system When the calibration event is performed by an external, commercial, ot independent calibration service supplier, the service supplier's calibration system can (or may) be verified through accreditation to ISO/IEC 17025. ‘When a qualified laboratory is not available for a given piece of equipment, calibration services may be performed by the equipment mannfactutet The measurement process TARGET is the “true” value of the part, It is desired that any individual reading be as close to this value as (economically) possible Unfortunately, the true valve can never be known with certainty However, uncertainty can be minimized by using a reference value based on a well defined operational definition of the characteristic, and using the results of a measurement system that has highet order disctimination and traceable to NIST. Because the reference value is used as a surrogate for the true value, these terms are commonly used interchangeably. This usage is not recommendedChapter I~ Section A | Introduction, Purpose and TerminologyThe Measurement Process Section B The Measurement Process‘ Measurement Systems In order to effectively manage variation of any process, there needs to be knowledge of: © What the process should be doing © What can go wrong © What the process is doing Specifications and engineering requirements define what the process should be doing The purpose of a Process Failure Mode Effects Analysis* (PFMEA) is to define the risk associated with potential process failures and to propose corrective action before these failures can occur. The outcome of the PEMEA is transferred to the control plan, Knowledge is gained of what the process is doing by evaluating the parameters ot results of the process. This activity, often called inspection, is | the act of exami plocess parameters, in-process parts, assembled subsystems, or complete end products with the aid of suitable standards and measuring deviecs which enable the observer to confirm or deny the premise that the process is operating in a stable manner with acceptable variation to a customer designated target. But this examination activity is itself a process General Process Input — No i | Output input | jperation utpul Process i tobe Managed Unfortunately, industry has traditionally viewed the measurement and analysis activity as a “black box” Equipment was the major focus ~ the more “important” the characteristic, the mote expensive the gage The > Portions of this chapter adapted with permission fiom Measurement Systems Analysis - A Tutorial by GF Gruska and M. § Heaphy, The Third Generation, 1987, 1998, * See the Potential Failure Mode and Ejfects Analysis (FMEA) Reference Manual ~ 4 Echtion 3B(Chapter E Section B The Measurement Process Statistical Properties of Measurement Systems usefulness of the instrument, its compatibility with the process and environment, and its usability was rarely questioned. Consequently these ‘gages were often not used properly or simply not used, ‘The measurement and analysis activity is a process —a measurement process Any and all of the management, statistical, and logical techniques of process control can be applied to it This means that the customers and their needs must first be identified The customer, the owner of the process, wants to make a correct decision with minimum effort Management must provide the resources to purchase equipment which is necessary and sufficient to do this But purchasing the best or the latest measurement technology will not necessarily guarantee correct production process control decisions Equipment is only one part of the measurement process. The owner of the process must know how to correctly use this equipment and how to analyze and interpret the results. Management must therefore also provide clear operational definitions and standards as well as training and support The owner of the process has, in turn, the obligation to monitor and control the measurement process to assure stable and correct results which includes a total measurement systems analysis perspective — the study of the gage, procedure, user, and environment; ic , normal operating conditions. ‘An ideal measurement system would produce only “correct” measurements cach time it is used. Each measurement would always agree with a standard ? ‘A measurement system that could produce measurements like that would be said to have the statistical properties of zero variance, zero bias, and zero probability of misclassifying any product it measured. Unfortunately, measurement systems with such desirable statistical properties seldom exist, and so process managers are typically forced to use measurement systems that have less desirable statistical properties The quality of a measurement system is usually determined solely by the statistical properties of the data it produces over time Other properties, such as cost, ease of use, ete , ate also important in that they contribute to the overall desirability of a measurement system. But itis the statistical properties of the data produced that determine the quality of the measurement system Statistical properties that are most important for one use are not necessarily the most important properties for another use, For instance, for some uses of @ coordinate measuring machine (CMM), the most important statistical properties are “small” bias and variance A CMM with those properties will ‘generate measurements that are “close” to the certified values of standards that are traceable, Data obtained from such a machine can be very useful for analyzing a manufacturing process. But, no matter how “small” the bias and variance of the CMM may be, the measurement system which uses the CMM may he unable to do an acceptable job of discriminating between good and bad product because of the additional sources of variation introduced by the other elements of the measurement system. 5 For a fuller discussion on the matter of standards see Out of the Crisis, W Edwards Deming, 1982, 1986, p. 279-281 4Sources of Variation The Measurement Process ‘Management has the responsibility for identifying the statistical properties that are the most important for the ultimate use of the data. Management is also responsible for ensuring that those properties ate used as the basis for selecting a measurement system. To accomplish this, operational definitions of the statistical properties, as well as acceptable methods of measuring them, are required Although each measurement system may be required to have different statistical properties, there are certain fundamental properties that define a “good” measurement system. These include: 1) Adequate discrimination and sensitivity. The increments of measute should be small relative to the process variation or specification limits for the purpose of measurement The commonly known Rule of Tens, or 10-t0-1 Rule, states that instrument discrimination should divide the tolerance (or process variation) into ten parts or mote This rule of thumb was intended as a practical minimum starting point for gage selection 2) The measurement system ought to be in statistical control FP6PF This means that under repeatable conditions, the vatiation in the measurement system is due to common causes only and not due to special causes This can be referred to as statistical stability and is best evaluated by graphical methods 3) For product control, variability of the measurement system must be small compared to the specification limits. Assess the measurement system to the feature tolerance 4) For process control, the variability of the measurement system ought to demonstrate effective resolution and be small compared to manufacturing process variation Assess the measurement system to the 6-sigma process variation and/or Total Variation from the MSA study The statistical properties of the measurement system may change as the items being measured vary If so, then the largest (worst) variation of the measurement system is small relative to the smaller of either the process variation or the specification limits. Similar to all processes, the measurement system is impacted by both random. and systematic sources of variation These sources of variation are due to common and special causes In order to control the measurement system variation: 1) Identify the potential sources of variation 2) Eliminate (whenever possible) ot monitor these sources of variation. Although the specific causes will depend on the situation, some typical sources of variation can be identified There ate various methods of The measurement analyst must always consider practical and statistical significance 15(Chapter 1-Section B The Measuremeat Process Standard W > Wotkpiece (ic. part) Instrument s i | P Person / Procedure E Environment presenting and categorizing these sources of variation such as cause-effect diagrams, fault tee diagrams, etc, but the guidelines presented here will focus on the major elements of a measuring system The actonym §.W IP E.” is used to represent the six essential elements of a generalized measuring system to assure attainment of required objectives SWIPE. stands for Standard, Workpiece, Instrument, Person and Procedure, and Environment. This may be thought of as an error model for @ complete measurement system * Factors affecting those six areas need to be understood so they can be controlled or eliminated. Figure [-B 1 displays a cause and effect diagram showing some of the potential sources of variation. Since the actual sources of variation affecting 2 specific measurement system will be unique to that system, this figure is, presented as a thought starter for developing a measurement system’s sources of variation This ecronym was originally developed by Ms. Mary Hoskins, a metrologist associated with Honeywell, Eli Whitney Metrology Lab and the Bendix Corporation © See Appendix F for an altemate error model, PIS MOEA. 16‘The Measurement Process Gesieiddy) uosiad sonuouotie Bupueysiopun epmime 5. vworque sq 2umIBJoduIO} 7 7 seams , ae Bauien ¥ Snub “sete “ ‘ é sqavedivoo wos eee ay vosezyenbe ajay Fae, spounduoa lips reuojievedo me Tet » 4 cue,” une ardosd Tore suonemum = voriijod we S161 ; rewi04 “ syep ae unten * cee Aayyqnedusco eo uavacho a ™ sunewsos8 levoneonps eueA iz = HEH “puepurig | weishg uswainseowy | oa 5 es sedan anon a overage . vorsuedee 4 ge « Aegeven ~, Mligesoen rewie4a 01200 Ty Ataeteede: soueuejuiew! ? « vwonesae9 foun ‘red wmunnoe ‘Aujowoe8 “ ‘on ¢ YaPPIY ‘naers ‘nveou sic sousrssu0o %__ Wohepen usp soumeat - swmep \ suwodans say a a eyenbepe ° sowedord vonewinyon ey Ae ons fyouoe8 eq Be pms » ssouyueeio ” uonewioep ‘sseursngos \ Pung A saw ‘onsere WOneOUICIE - UB isep uoreuen SONSUBTOEIEUO suoydunese a a ping pavejeuaqu en apardyiom | Figure -B 1: Measurement System Variability Cause and Effect Diagram‘Chapter I~ Seetion B The Measurement Process The Effects of Measurement System Variability Effect on Decisions Because the measurement system can be affected by various sources of variation, repeated readings on the same part do not yield the same, identical result Readings vary from each other due to common and special causes. ‘The effects of the various sources of variation on the measurement system. should be evaluated over a short and long petiod of time. The measwement system capability is the measurement system (random) etror over a short period of time. It is the combination of errors quantified by linearity, uniformity, repeatability and reproducibility. The measurement system performance, as with process performance, is the effect of all sources of variation over time. This is accomplished by determining whether our process is in statistical control (ie,, stable and consistent; variation is due ‘only to common causes), on target (no bias), and has acceptable variation (gage repeatability and reproducibility (GRR)) over the range of expected results. This adds stability and consistency to the measurement system capability | Because the output of the measurement system is used in making a | decision about the product and the process, the cumulative effect of all | the sources of variation is offen called measurement system error, or / sometimes just “error” After measuring a part, one of the actions that can be taken is to determine the status of that part, Historically, it would be determined if the part were acceptable (within specification) or unacceptable (outside specification) Another common scenario is the classification of parts into specific categories (e g , piston sizes) | For the rest of the discussion, as an example, the two category situation will be used: out of specification ("bad") and in specification | (’good"), This does not restrict the application of the discussion to other categorization activities, Further classifications may be reworkable, salvageable or scrap. Under a product control philosophy this classification activity would be the primary reason for measuring 2 part. But, with a process contro? philosophy, interest is focused on whether the part variation is due to common causes ot special causes in the process Philosophy Interest Product contro! Is the partin a specific category? Process control Is the process variation stable and acceptable? Table I-B1: Control Philosophy and Driving Interest‘The Measurement Process The next section deals with the effect of the measurement error on the product decision. Following that is a section which addresses its impact on the process decision ————-—_ In order to better understand the effect of measurement system error on. Effect on product decisions, consider the case where all of the vatiability in multiple Product readings of a single partis due to the gage repeatability and reproducibility et That is, the measurement process is in statistical control and has zero bias Decisions ‘A wrong decision will sometimes be made whenever any part of the above ‘measurement distribution overlaps a specification limit. For example, a good part will sometimes be called “bad” (type I ertor, producer's risk ot false alarm) if: ‘And, a bad part will sometimes be called “good” (type IT error, consumer's risk or miss rate) if LSL NOTE: False Alarm Rate + Miss Rate = Error Rate RISK is the chance of making a decision which will be detrimental to an individual or process That is, with respect to the specification limits, the potential to make the wrong decision about the part exists only when the measurement system error intersects the specification limits This gives three distinct areasChapter I~ Section B The Measurement Process Effect on Process Decisions where: 1 Bad parts will slways be called bad Tl Potential wrong decision can be made IN Good parts will always be called good Since the goal is to maximize CORRECT decisions regarding product status, there are two choices: 1) Improve the production process: reduce the variability of the process so that no parts will be produced in the II or “shaded” areas of the graphic above 2) Improve the measurement system: reduce the measurement system errot to reduce the size of the II areas so that all parts being produced will fall within area I and thus minimize the risk of making a wrong decision This discussion assumes that the measurement process is in statistical control and on target If either of these assumptions is violated then there is little confidence that any observed value would lead to a correct decision, With process control, the following needs to be established: + Statistical control © Ontarget © Acceptable variability ‘As explained in the previous section, the measurement error can cause incorrect decisions about the product The impact on process decisions would be as follows: © Calling a common cause a special cause + Calling a special cause a common cause Measurement system variability can affect the decision regarding the stability, target and variation of a process The basic relationship between the actual and the observed process vaviation is: 20The Measurement Process Sn = Front + Fr where , = observed process variance C2 gq; = actual process variance vatiance of the measurement system, The capability index? Cp is defined as Cp = HeleranceRange 60 The relationship between the Cp index of the observed process and the Cp indices of the actual process and the measurement system is derived by substituting the equation for Cp into the observed variance equation above: (CP) = (PMs *(P Ye Assuming the measurement system is in statistical control and on target, the actual process Cp can be compared graphically to the observed Cp." Therefore the observed process capability is a combination of the actual process capability plus the variation due to the measurement process To reach a specific process capability goal would require factoring in the measurement vatiation For example, if the measurement system Cp index were 2, the actual process would require a Cp index greater than or equal to 1.79 in order for the calculated (observed) index to be 1 33. If the measurement system Cp index were itself 133, the process would require no variation at all if the final result were to be 1.33 ~ clearly an impossible situation * Although this discussion is using Cp, the results hold also for the performance index Fp © See Appendix B for formulas and graphs aq