Machine Learning based Approach for the Prediction of Surface Integrity in Machining

This paper presents a two-stage procedure to create a surface integrity predictor. The first stage includes data clustering, which allows to evaluate the achievable surface quality. The second stage consists in training the model to predict which cluster the machined surface will belong to. To demonstrate the applicability, an experimental plan for machining of Inconel 718 in milling was developed. The validation through confusion matrix showed that the accuracy of prediction ranged from 64.7% to 84.9% for different test and train sets. Prospect of the research is to expand the set of monitored machining parameters and controlled surface integrity parameters.