The methodology proposed in this study – for time errors detection for dental pieces manufacturing –
in a first step aims to detect the ability of the data set to be modeled.
In this step PCA and CMLHL have been the used techniques and they show that data are sufficiently informative and can be
modeled in a next step with guarantees of success.
Finally, different techniques -supervised neural model- are applied to obtain a suitable model,
which will be responsible for detecting the time errors for dental pieces manufacturing.