IDENTIFICATION OF PRE-SLIDING AND SLIDING FRICTION

The nonlinear dependence of pre-sliding and sliding friction forces on displacement and velocity is modelled using different physics-based and black-box approaches including various Maxwell-slip models, NARX models, neural networks, nonparametric (local) models and recurrent networks. The efficiency and accuracy of these identification methods is compared for an experimental time series where the observed friction force is predicted from the measured displacement and velocity. All models, although varying in their degree of accuracy, show good prediction capability of friction. Finally, it is shown that better results can be achieved by using an ensemble of the best models for prediction.