Quality Prediction of Honed Bores with Machine Learning Based on Machining and Quality Data to Improve the Honing Process Control

摘要

Honing mostly describes the last step in the production stage and is a machining process that produces precise elements regarding form, geometry and surface quality. Process control is a crucial point in order to meet these high-quality demands. A new approach to further improve this process could be to predict the quality based on data and machine learning algorithms. In this paper, the machine learning method of random forests (RF) is employed to predict dimensional and surface quality characteristics of honed bores. Process data was collected during test series.