Data-driven modeling for electro-active liquid crystal polymer networks

In this paper, we propose a data-driven nonlinear modeling approach to describe the dynamics of smart surfaces composed of electroactive liquid crystal networks (LCNs). LCNs are among the top candidates for materials to be employed in smart surfaces such as haptic displays. To realize such applications, the ability to predict an accurate LCN surface response as a function of the input signal is crucial. In this paper, we propose a data-driven modeling approach to identify the parameters of a dynamic model based on experimental data. The resulting model is used for feedforward control to compute the appropriate excitation parameters that ensure a certain desired surface deformation. This feedforward control approach is validated in a simulation study.