Das Ansteuern von Compliant-Mechanismen zu Zielpositionen ist besonders
herausfordernd, da analytische Modelle die inverse Kinematik
nicht oder nur teilweise aufstellen können. Anhand eines beispielhaften
Compliant-Mechanismus zeigt diese Arbeit wie Methoden des Machine
Learning angewandt werden können, um die entsprechende Kinematik
erfolgreich zu lernen. Damit sind Aussagen über die Ansteuerungen der
Aktuatoren möglich, mit deren beliebige Punkte mit dem Mechanismus
erreicht werden.
Controlling of compliant-mechanisms with reinforcement learning
Driving compliant-mechanisms to target positions is particularly challenging
since it is not or hardly possible to set up the inverse kinematics with
analytical models. On the basis of an exemplary compliant-mechanism,
this work shows how machine learning methods can be applied to successfully
learn the corresponding kinematics. This allows statements
on how the actuators have to be controlled in order to reach arbitrary
points with the mechanism.
Electrically conductive fibers are required for numerous fields of application in modern textile technology. They are of particular importance in the manufacturing of smart textiles and fiber composite systems with textile-based sensor and actuator systems. Elastic and electrically conductive filaments can be used as strain sensors for monitoring the mechanical loading of critical components. In order to produce such sensorial filaments, thermoplastic polyurethane (TPU) is compounded with carbon nanotubes (CNT) and melt spun. The mechanical performances of filaments produced at different spinning speeds and containing different amounts of CNT were tested. Furthermore, the correlation between the specific electrical resistance of the filaments and the mechanical strain were analyzed depending on the CNT-content and the spinning speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.