Position tracking accuracy of mechatronics is limited by the presence of disturbances, which originate from unmodelled or unforeseen deterministicenvironmental effects . To negate the effects of these disturbances, a learningbased feedforward controller is employed, where the underlying control policy is estimated from experimental data based on Gaussian Process regression . The effectiveness of the augmentation is experimentally validated on amagnetically levitated planar motor stage . The results of this paperdemonstrate the benefits and possibilities of machine-learning based approaches for compensation of static effects, such that position tracking performance for moving-magnet planar Motor Actuators is improved, such as improved position tracking accuracy for moving motor actuators . The proposed approach exploits the property of including prior knowledge on the expected steady state

Author(s) : Ioannis Proimadis, Yorick Broens, Roland Tóth, Hans Butler

Links : PDF - Abstract

Code :



Keywords : based - effects - tracking - motor - planar -

Leave a Reply

Your email address will not be published. Required fields are marked *