capability制程能力学习.pptxVIP

1 Assessing Process Capability for Variable Data Verify Specification and Measurement System Take a short term or long term sample Verify Process Stability Calculate Cp, Cpk, Pp, Ppk, DPU and PPM Calculate Z-score short term and long term (Sigma Level) 第1页/共31页 2 This transform produces a value from a distribution where the Mean = 0 and  = 1. The value indicates how far the number is from the mean in units of standard deviations. For example, if Z = 2, that would say that the number in question is 2 standard deviations away from the Mean. For estimating our yield for a process, we will substitute the Lower Spec Limit (LSL) and the Upper Spec Limit (USL) for x. By using this method, we can calculate the proportion of product that is out-of-spec based on that products Output Mean and . Let’ s look at an example. The Standard Transform 第2页/共31页 3 Z-Transform Example Mean = 1.03 LSL = 0.90  = 0.0573 USL = 1.10 第3页/共31页 4 Z-Transform The task is to determine estimates of the proportion of the normal curve that is outside the upper and lower specification limits. We do that by calculating Z-score for each spec limit. We can now calculate the areas below the lower spec and above the upper spec using the normal probability function. 第4页/共31页 5 Example Standard Score Distribution Raw Score Distribution 第5页/共31页 6 Example The Fraction Outside the Spec Limits can be determined by using Normal Table or Minitab Functions. Where do we get the probabilities? The Normal Table or Minitab. CalcProbability DistributionNormalCumulative Probability . 第6页/共31页 7 Relating Z-Scores to Six Sigma To Achieve Six Sigma, the Z-scores for the USL and LSL should be at least 6.00 each in a short-term capability Study. That says that the mean of the distribution is six standard deviations away from the spec limit. To calculate the Z- score for the process, we must use the following procedure: