Process cap for PDF - ASQ

1 March 2006 Copyright 2006 Sanjaya Kumar SaxenaProcess CapabilitybySanjaya Kumar SaxenaThe capability of a Process is a statistical indicator of how well it is functioning, or, inother words, how successful it is at running within its specified the absence of any special orassignable causes ofvariation, a Process will still havesome inherent variability. Process capability is a statistical measure of this we wish to set up a Process for manufacturing ordinary washers, thin diskswithholes in the middle, used to support the loads of threaded requirement is that our washers should have an inner diameter of cm.

2 This is thetarget, or mean. A maximum acceptable variation is cm. Any variation beyondacceptable limits is considered a defect. For example, a washer having an inner diameterof cm will be marked as put, the inner diameter specifications are cm. This tolerance or acceptable variation is cm(the spread of tolerance). lower specification limit, referred to as LSL, is cm ( ). upper specification limit, referred to as USL, is cm ( + ). target, or mean, diameter is , our manufacturing processwill be a capable one provided it has a mean equalto the target of cm and variation less than the specified tolerance or acceptablevariation of addition, there should not be any special cause of variation.

3 In other words, the processshould be under Process CapabilityWhen computing Process capability, there is a distinction to be made regarding thecurrent and future ability of the Process and its past performance. Here we will focus onthe performance of 2006 Sanjaya Kumar Saxena2 Table 1 presents four common mathematical expressions to compute processperformanceunder different 1 Computing processperformancePpis a good measure when the Process is centeredin the middle of USL and LSL. 6 LSLUSLPp Ppuis used for processes that have only an upperspecification limit. See the 30-minute pizzadelivery example in Delight Your Customers theSix Sigma Way.

4 3 USLPpuPplis used for processes that have only a lowerspecification limit. 3 LSLPpl Ppkis a good measure when the Process is notexactly centered in the middle of USL and LSL. puplpkPPP,min For a capable Process , these values should be equal to or greater than The commonlyrecommended value is or equal to , then only of the washers produced will be defective, providedtheir inner diameters follow the normal distribution. Wondering why?Simply refer tothe Six Sigma Forum beginner article Delight Your Customers the SixSigma Way, which explains the following characteristics of a normal distribution: 68% of the data points fall within the area of-1 and +1 on either side of the mean.

5 Approximately fall within 2 on either side. fall within 3 on either side ( to be a little more precise).If Pp = , only (100- )%, or , of the washers will have inner diametersbeyond USL or 2 contains sample inner-diameter data for four different each Process is computed using MINITAB, a statisticalsoftware, asillustrated in figure 1 below. Review each chart 2006 Sanjaya Kumar Saxena3 Table 2 Inner diamaters, in centimeters,of washers produced by four 2006 Sanjaya Kumar Saxena4 Figure 1 Processperformancefor four processesCopyright 2006 Sanjaya Kumar Saxena5 Figure 1(continued) Process performance for four processesCopyright 2006 Sanjaya Kumar Saxena6 Process capability applies to virtually all processes, from traditional manufacturingprocesses, to software, services, healthcare, and telecom, to insurance.

6 No matterwhatprocess is under analysis, it is important to remember that it probably does not operate inisolation. In order to achieve good internal Process capability, the capability of processessupplying inputs must also be the AuthorSanjaya Kumar Saxena has more than twenty-two years of experience in the softwareindustry, including extensive experience with business Process management andinformation security. He holds a bachelor s of technology in electrical engineering, hasserved as guest faculty at premier Indian management institutes, and authorsDiscover SixSigma, a blog to support the application of Six Sigma in different business member of IEEE, Sanjaya works for Pre-emptive Systems (P) Limited.