R&R Analysis for Destructive Measurements

Destructive vs. non-destructive tests:

• With non-destructive measurements, data for GR&R studies are collected by measuring the same part or sample several times, using the same measurement device, with measurements conducted by the same appraiser.

• With destructive measurements, we cannot use the same part or sample again; by definition, it is consumed or destroyed.

• Since we cannot repeat measurements on the same part or sample, we must use techniques to separate sample-to-sample variation from actual measurement system variation.

Homogenous samples:

• The best approach, when possible, is to ensure homogenous samples are used. If we can create nearly homogenous samples, we can assume the samples are essentially equal and perform the analysis exactly the same way as it was done with non-destructive measurements.

When you cannot create homogenous samples:

• When homogenous samples cannot be created, the repeatability inherent within the equipment used to prepare the test specimen and the repeatability (or variation) within the material are confounded.

• The use of ANOVA techniques allows us to determine if the impact of test specimen preparation is statistically significant.