Mechatronics applications of condition monitoring using a statistical change detection method

M. Mazzoleni, M. Scandella, F. Previdi

In this paper, we propose the use of a statistical change detection method to perform condition monitoring of mechanical components. The aim is to look for statistical changes in the distribution of features extracted from raw measurements, such as Root Mean Square or Crest Factor indicators. The proposed method works in a batch fashion, comparing data from one experiment to another. When these distributions differ by a specified amount, we detect a degradation of the system under study. We define an evaluation policy for comparing experiments, which is sensible to system changes. The proposed approach is tested on two experimental industrial applications: (i) an Electro-Mechanical Actuator employed in flight applications, where the focus of the monitoring is on the ballscrew transmission; (ii) a CNC workbench, where the focus is on the vertical axe bearing. Both components undergone a severe experimental degradation process, that ultimately led to their failure. Results show how the proposed method is able to assess components degradation prior to their failure.