SID-Net: machine learning based system identification framework for rigid and flexible multibody dynamics

Modeling and simulation of dynamic systems are widely used in mechanical system design and control. System identification, a process of correlation using experimental or target data, is essential for the reliability of implemented numerical models. To actualize the process, it is crucial to understand the relationship between numerous modeling parameters that affect the system’s responses. Modeling and simulating nonlinear systems, such as multibody dynamics, involves complexity due to the fundamental assumptions and approximations of their characteristics; furthermore, the computational demands are also crucial during the iterative system identification process. Therefore, we propose an effective system identification framework for rigid and flexible multibody dynamics using artificial neural networks. The framework consists of two phases: a system metamodel and a parameter estimation network. Through supervised learning, a metamodel capable of providing nonlinear time-transient responses based on the input system design parameters in real time was generated. A loss minimization procedure is introduced to update the trainable parameters in the parameter estimation network, which identifies input design parameters for generating the desired target output. The loss function was designed to minimize the difference between the system metamodel’s output and the target output. The performance of the proposed framework was evaluated using well-designed numerical and experimental examples.