Welcome to the research group on
"Data-driven Nonlinear Mechanics" at KU Leuven
The group academic leader is Prof. dr. Jean-Philippe Noël. We are affiliated with the Mecha(tro)nic System Dynamics Division of the Mechanical Engineering Department at KU Leuven
Our Activities at a Glance
Our research focuses on the development of data-driven methodologies to model, control and design dynamic systems that are relevant to mechanical engineering. A recurrent subject of interest concerns the impact of nonlinearities on these systems. We address the full spectrum of topics in data-driven dynamics from test preparation, data acquisition and model construction to controller implementation and design optimisation. The originality of our work lies in a constant effort to apply to mechanical problems ideas and tools emerging in neighbouring fields, in particular in machine learning, control theory and nonlinear dynamics.
We also teach at Bachelor and Master levels within the Faculty of Engineering Technology at KU Leuven. Our duties includes classes on mechanical vibrations, machine components, finite elements, and digital twins.
We finally participate actively in the life and outreach of our scientific community. Every year, we attend conferences, visit labs, deliver research talks, review journal papers, co-organise short-courses, sessions and workshops, sit in doctoral committees, and provide consultancy services. Prof. Noël is also a member of the editorial board of the Mechanical Systems and Signal Processing journal.
Data-driven feedback linearisation using model predictive control
Linearising the dynamics of nonlinear mechanical systems is an important and open research area. In this paper, we adopt a data-driven and feedback control approach to tackle this problem. A model predictive control architecture is developed that builds upon data-driven dynamic models obtained using nonlinear system identification.