Data-driven observer design for an inertia wheel pendulum with static friction

TL;DR

This paper introduces a data-driven observer design for an inertia wheel pendulum that accounts for static friction by identifying switching nonlinear dynamics through machine learning and integrating them into a moving horizon estimator.

Contribution

It presents a novel data-driven approach to model static friction effects and switch dynamics in an inertia wheel pendulum for improved state estimation.

Findings

Successful identification of switching dynamics using machine learning methods.

Effective state estimation with the proposed observer in the presence of static friction.

Enhanced modeling of frictional effects improves control accuracy.

Abstract

An indirect data-driven state observer design approach for the inertia wheel pendulum considering static friction of the actuated inertia disc is presented. The frictional forces occurring in a real laboratory setup are characterized by the Stribeck effect as well as the transition between two different dynamic behaviors, sticking and non-sticking. These switching nonlinear dynamics are identified with various machine learning methodologies in a data-driven manner, i.e., the unsupervised separation and feature clustering of measured state trajectories into two dynamic classes, and the supervised classification of a state-dependent switching condition. The identified system with the interior switching-structure of two dynamics is combined with a moving horizon estimator.