Predictive maintenance of a rotating condenser inside a synchrocyclotron
We investigate data-driven methods to predict failures of a rotating condenser inside a synchrocyclotron for a proton therapy treatment system. The aim is to predict failures of the bearing box which contains the shaft and the bearing elements. Several sensors within the cyclotron are constantly measuring multiple signals. We leverage those time-series data to predict a few days in advance whether a failure is likely to happen.
Valentin received his engineering degree in applied mathematics in 2017. He started a PhD in October 2018 at UCLouvain in the mathematical engineering department in partnership with IBA (Ion Beam Applications). His thesis is about predictive maintenance applied to proton therapy machines.