NEWS 28 February 2023

A mechatronic Machine Learning case

To date, Machine Learning (ML) has found only relatively limited implementation in high-end mechatronic systems. To test its capabilities in a real industrial application, the challenging case of friction estimation was investigated.


A model was developed for predicting frictional properties of linear ball bearings, for very small displacements, as explained in this Mikroniek article. The resulting ML model performed well during training and validation, but rather less so in stand-alone operation. ML is a promising tool for friction estimation, but clearly there is room for improvement in algorithm development. (Image courtesy of Jorn Veenendaal)


References

Picometer drift and microrad reproducibility

At the end of May, Settels Savenije hosted a DSPE Knowledge Day dedicated to challenges in nanometrology.

Read more
Order of frictions and stiffnesses…

For lumped systems consisting of different frictions and stiffnesses, there has been confusion in literature about hysteresis curves and virtual play for many decades.

Read more
Make it clean

In mid-April, the second edition of the Manufacturing Technology Conference and the fifth edition of the Clean Event were held together, for the first time, at the Koningshof in Veldhoven (NL).

Read more