Data-driven Modeling and Simulation of a double Spring Mass Damper System For the double spring mass damper system, there are only measurement data for the position of mass 1 and partial differential equation and initial conditions for mass 2. From these imperfect data and physics, the system response can be modeled and simulated in real-time based on the physic-informed machine learning. The simulation and measurement of the system response coincides totally. This novel technology show case presents the new way, how to model the system from any mix of data and physical components as partial differential equation, initial conditions and constraints.More

New Version OptiY 4.7 We are proud to announce the release of the new version OptiY 4.7. It provides a novel framework of Hilbert space for modeling and simulation based on physics-informed machine learning. The so-called meta-modeling presents a new way and it is an user-defined mix of some imperfect data and some imperfect physical components as partial differential equation, boundary or initial conditions and constraints. Thus, complex multi-physics-systems with different disciplinary and interactive fields as fluid, energy, thermal, electro-mechanics, magnetisms etc.. can be modeled and simulated for real-time computing. Dynamical system with strong nonlinear response can also captured into the framework. Nonlinear autoregressive exogenous model can used for discovery of unknown partial differential equations. It is a big innovation with big potential, explore these possibilities! More