This study will be explained from the example below.
5,15 sigma = RR Þ 5,15 = 0,25 Þ sigma = 0,04854
Example of hom to create the performance curve of a device:

First Device Performance Curve Point (79,95)
X = 79,95 – 0,1 = 79,85Z = (ILE – X) / sigma = (80 – 79,85) / 0,04854 Þ Z = 3,09 Þ P(Z) = 0,10%
Z = (SLE – X) / sigma = (82 – 79,85) / 0,04854 Þ Z = 44,29 Þ P(Z) = 0,00%
ps.: P(Z) = 0.10% is extracted from the normal distribution table for Z = 3,09

Second Device Performance Curve Point (81)
X = 81 – 0,1 = 80,9Z = (X – ILE) / sigma = (80,9 – 80) / 0,04854 Þ Z = 18,54 Þ P(Z) = 0,00%
Z = (SLE – X) / sigma = (82 – 80,9) / 0,04854 Þ Z = 22,66 Þ P(Z) = 0,00%

Third Device Performance Curve Point (82)
X = 82 – 0,1 = 81,9Z = (X – ILE) / sigma = (81,9 – 80) / 0,04854 Þ Z = 39,14 Þ P(Z) = 0,00%
Z = (SLE – X) / sigma = (82 – 81,9) / 0,04854 Þ Z = 2,06 Þ P(Z) = 1,97%

Fourth Device Performance Curve Point (82,04)
X = 82,04 – 0,1 = 81,94Z = (X – ILE) / sigma = (81,94 – 80) / 0,04854 Þ Z = 39,96 Þ P(Z) = 0,00%
Z = (SLE – X) / sigma = (82 – 81,94) / 0,04854 Þ Z = 1,24 Þ P(Z) = 10,82%

Fifth Device Performance Curve Point (82,12)
X = 82,12 – 0,1 = 82,02Z = (X – ILE) / sigma = (82,02 – 80) / 0,04854 Þ Z = 41,61 Þ P(Z) = 0,00%
Z = (X - SLE) / sigma = (82,02 – 82) / 0,04854 Þ Z = 0,41 Þ P(Z) = 34,02%
After accomplishing all the calculations and tracing the curve, for the resulting value of each part, the mode graph shall be used in order to know the probability of acceptance for each related part. In the X axis of the graph, the value found for the part that is being analysed has to be entered and an imaginary line has to be created an then, from the found value, until this imaginary line reaches the graph and, at this moment, it is read in the Y”axis the probability of acceptance.
The technician responsible for the analysis ha to evaluate the importance of the characteristic to be controlled to define whether the study should be accomplished or not, due to its complexity.
The performance curve of a device’s objective is solely and exclusively to evaluate the probability of acceptance of each measured part. This study allows us a higher safety margin in decisions such as: to liberate or scrap a batch of manufactured parts as well as to invest in financial resources to improve the RR values or even to reduce the device’s tendency value. The smaller the RR values and the bias are the higher is the probability of acceptance for the values near the engineering limits.