Identification of physically realistic state-space models for accurate component synthesis

Journal article, 2020

For components that are difficult to model with conventional analytical or numerical tools, experimentally derived state-space models can instead be used in system synthesis. For successful state-space synthesis, a physically realistic model must be identified. For this purpose, a hybrid first- and second-order system description is used here as the basis for identification. In the identification procedure, a physically motivated rigid body rank constraint is imposed together with a reciprocity constraint. The two constraints are enforced during a re-estimation phase of the state-space matrices following after a traditional state-space subspace identification phase. In this paper, two complex and modally dense industrial components are combined into a dynamical system. An experimental model of a car body-in-white structure is identified. The identified subsystem model is coupled with a finite element model of a rear subframe in a system synthesis. The two subsystems are attached through four rubber bushings modelled by finite element procedures. It is shown that the experimental-analytical assembly successfully predicts the reference measured system, with higher accuracy than what could be achieved with a model based solely on finite elements. It is also shown that synthesis with individually calibrated rear subframe models can capture the variability in the coupled system.