Research on the uncertainties from different form error evaluation methods by CMM sampling

As a part of the new measurement uncertainty system proposed in the new generation of Geometrical Product Specifications and Verification, the evaluation methods of uncertainties to form errors have been researched in mechanical engineering, which are calculated based on the error propagation principle and statistical concept under certain conditions. In this paper, the evaluation datum is obtained by using both the least squares method and the genetic optimization algorithm. Their computation uncertainties to flatness and roundness were compared with each other using the sample data from a coordinate measurement machine (CMM). The results show that the uncertainties obtained from the genetic algorithm-based method are similar to those from the least squares method according to their evaluation parameters. The evaluation uncertainties from different methods become a little smaller with more sample points. A more significant conclusion is that the evaluation uncertainties from two methods are so small that they almost do not affect the measurement uncertainties to form error, which, in fact, mainly comes from the CMM sampling. Therefore, for the efficiency and simplification of calculation, especially for the cylintricity with more parameters, the uncertainties from evaluation methods can be neglected where the precision is not so strict.