1、Designation: D 4583 95 (Reapproved 2009)Standard Practice forCarbon BlackCalculation of Process Indexes From anAnalysis of Process Control Data1This standard is issued under the fixed designation D 4583; the number immediately following the designation indicates the year oforiginal adoption or, in t
2、he case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. Asuperscript epsilon () indicates an editorial change since the last revision or reapproval.1. Scope1.1 This practice covers (1) a statistical procedure foranalyzing the test data generated
3、 in the statistical processcontrol of a carbon black manufacturing process; (2) a formatfor reporting process capability determined from the analysisof control chart data of an individual production run, and (3)aformat for reporting process performance determined from theanalysis of control chart da
4、ta of an individual production run.1.2 This practice specifically applies to the analysis ofpelleted carbon black samples taken during the manufacturingprocess prior to storage. This practice does not apply toshipment samples taken from hopper cars or other containers orpackages.1.3 This practice is
5、 specifically designed to be used forthose test methods given in Classification D 1765 whichspecify target values. However, these techniques are applicableto other test methods on carbon black.1.4 This practice describes the calculation for two methodsof determining capability factors from an analys
6、is of processcontrol data.1.4.1 Process capability (Cp) is a measurement of variationcalculated from the process control chart data with the use ofan estimated standard deviation (s) from the mean value of themoving range (R) chart. The calculation of the process capa-bility (Cp and Cpk) indexes can
7、 be used as historical informa-tion or to predict future performance of the process, but areonly valid when the process is in a state of statistical control.1.4.2 Process performance (Pp) is a measurement of varia-tion calculated from the process control chart data usingsample standard deviation(s).
8、 The calculation of the processperformance (Pp and Ppk) indexes are used for a historicalreference of a process performance and does not require astate of statistical control.2. Referenced Documents2.1 ASTM Standards:2D 1765 Classification System for Carbon Blacks Used inRubber Products3. Terminolog
9、y3.1 Definitions of Terms Specific to This Standard:3, 43.1.1 average moving range ( R )the arithmetic mean of nmoving ranges, R = (R/n.3.1.2 Cpk indexan index that indicates how well thecommon cause process variability is actually contained withinthe specifications. (See 6.4.)3.1.3 moving range (R)
10、the absolute difference betweenconsecutive, individual test values.3.1.4 Ppk indexindicates how well the common andspecial cause process variability is actually contained withinthe specifications. (See 6.6.)3.1.5 process capability index (Cp)an index that com-pares the magnitude of common cause proc
11、ess variability to therange of upper and lower specification limits (USL and LSL)without regard to where the process is centered; Cpindex = (USL LSL)/(6s). (See 6.3.)3.1.6 process performance index(Pp)an index that com-pares the magnitude of common and special cause processvariability to the range o
12、f the upper and lower specificationlimits (USL and LSL) without regard to where the process iscentered; Pp index = (USL LSL)/(6s). (See 6.5.)4. Significance and Use4.1 This practice will provide the following: (1) a statisticalsummary of individual production run data plotted on a control1This pract
13、ice is under the jurisdiction of ASTM Committee D24 on CarbonBlack and is the direct responsibility of Subcommittee D24.61 on Carbon BlackSampling and Statistical Analysis.Current edition approved May 1, 2009. Published May 2009. Originallyapproved in 1986. Last previous edition approved in 2004 as
14、D 4583 95 (2004).2For referenced ASTM standards, visit the ASTM website, www.astm.org, orcontact ASTM Customer Service at serviceastm.org. For Annual Book of ASTMStandards volume information, refer to the standards Document Summary page onthe ASTM website.3Manual on Presentation of Data and Control
15、Chart Analysis, STP 15D, ASTMInternational, 1976.4Ford Motor Company Manual on “Process Capability and Continuing ProcessControl,” Publication No. 80-01-251. Available in packs of five from Ford MotorCompany, Statistical Methods Publications, P.O. Box 1000, Plymouth, MI 48170.1Copyright ASTM Interna
16、tional, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959, United States.chart; (2) a statistical summary of data from multiple produc-tion runs; (3) a procedure to relate the average and variation ofthese data groups to specification limits, and (4) indexes forcomparing different
17、 manufacturing units for projecting futurecapabilities or as historical reference.5. Procedure5.1 Sampling:5.1.1 In order to provide uniformity and the ability to makevalid comparisons of process capability and process perfor-mance indexes, all samples used for these calculations shall becollected i
18、n the same way. Samples that are to be tested forproperties on which capability or performance indexes will becalculated shall be collected as follows:5.1.1.1 All samples shall be taken from the process at thefinished pellet discharge and tested individually. Compositingof samples is not permitted.5
19、.1.1.2 Samples normally shall be taken every 4 h. Allresults obtained on material that is put into finished productstorage tanks shall be included.5.1.1.3 Averaging of results is not permitted. Each result, asdefined by the appropriate test method, is to be recorded andused in performing the calcula
20、tions described in Section 6.5.2 Process Capability:5.2.1 A minimum of 30 test data generated during produc-tion periods in which the process is in statistical control arerecommended for estimating a process capability standarddeviation. In that case, the number (n) of moving rangesaveraged will be
21、29.5.2.2 Calculate Cp and Cpk as shown in 6.3 and 6.4. The Cpindex and the Cpk index must be greater than 1.00 in order toindicate the capability of the process to meet the establishedspecifications. The Cpk index is inherently less than or equal tothe Cp index (for one-sided specifications, only th
22、e Cpk indexis applicable).5.2.3 The Cp index indicates whether or not the process iscapable of meeting a specification. Maximum performance isachieved when the process is perfectly centered and the Cpk isequal to the Cp.5.2.4 In comparing one manufacturing unit to another, thelarger Cpk index demons
23、trates a greater capability to conformto the specification range of the specified property.5.2.5 A process capability summary can be used to evaluatea production unit over a period of time such as weekly,monthly, or quarterly. (See Fig. 1.) After each production run,or after 30 or so tests, the valu
24、es of n, x, 6 difference fromtarget, MR,3s, Cp, and Cpk are recorded on the summaryform. At the conclusion of the appropriate time interval, thegrand average x !5, average difference from target, average Cp,and average Cpk can be displayed at the foot of the appropriatecolumn. These average values,
25、especially the Cpk, can be usedto compare the quality levels of different manufacturing units.FIG. 1 Sample Process Capability Summary SheetD 4583 95 (2009)25.3 Process Performance:5.3.1 A minimum of 30 test data are required, withoutregard to the process being in a state of statistical control, whe
26、ncalculating the standard deviation for process performance. Inthis case, extended production periods such as weeks ormonths can be represented.5.3.2 Calculate Pp and Ppk as shown in 6.5 and 6.6. Boththe Pp index and Ppk index must be greater than 1.0 in orderto indicate that the process meets speci
27、fications. The Ppk indexis inherently less than or equal to the Pp index (for one-sidedspecifications, only the Ppk is applicable).5.3.3 A process performance summary can be used tosummarize the data generated by the different productionperiods represented in a row of calculated values. (See Fig. 2.
28、)6. Calculation6.1 Calculate estimated standard deviation (s) as follows:s ! 5Rd2(1)where:d2= 1.128 for n =2.6.2 Calculate sample standard deviation as follows:s 5(i 5 1nXi2! 2 X(i 5 1nXi!n 2 1(2)where:s = sample standard deviation,n = number of tests,Xi= individual test results, andX= average of al
29、l test results.6.3 Calculate the Cp index as follows:Cp index 5USL 2 LSL6s(3)where:USL = the upper specification limit,LSL = the lower specification limit, ands = the process capability estimated standard deviation.6.4 Calculate the Cpk index as follows:Cpk index 5 minimum ratio of: (4)USL 2 X3sorX2
30、 LSL3s(5)where:X= the process average, ands = the estimated standard deviation.6.5 Calculate the Pp index as follows:Pp index 5USL 2 LSL6s(6)6.6 Calculate the Ppk index as follows:Ppk index 5 minimum ratio of: (7)USL 2 X3sorX2 LSL3s(8)where:X= the process average, ands = the sample standard deviatio
31、n.7. Keywords7.1 carbon black;Cp index;Cpk index; moving range; pro-cess capability; process capability from test data; processcontrolPROCESS PERFORMANCE SUMMARYPLANT: _ UNIT: _ GRADE: _ PROPERTY: _ AS OF DATE: _MATERIAL SPEC: _RANGE: _TARGET: _Production Period n XDifference 6 Target 3s Pp PpkFIG.
32、2 Sample Process Performance Summary SheetD 4583 95 (2009)3ASTM International takes no position respecting the validity of any patent rights asserted in connection with any item mentionedin this standard. Users of this standard are expressly advised that determination of the validity of any such pat
33、ent rights, and the riskof infringement of such rights, are entirely their own responsibility.This standard is subject to revision at any time by the responsible technical committee and must be reviewed every five years andif not revised, either reapproved or withdrawn. Your comments are invited eit
34、her for revision of this standard or for additional standardsand should be addressed to ASTM International Headquarters. Your comments will receive careful consideration at a meeting of theresponsible technical committee, which you may attend. If you feel that your comments have not received a fair
35、hearing you shouldmake your views known to the ASTM Committee on Standards, at the address shown below.This standard is copyrighted by ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959,United States. Individual reprints (single or multiple copies) of this standard may be obtained by contacting ASTM at the aboveaddress or at 610-832-9585 (phone), 610-832-9555 (fax), or serviceastm.org (e-mail); or through the ASTM website(www.astm.org).D 4583 95 (2009)4
