Identifying the ODE in a system of nonlinear ordinary differential equations is critical to designing a robust controller. However, if the system is stochastic in nature or if only noisy measurements are available, standard optimization algorithms for system identification usually fail. We present a novel approach that combines recent advances in physics-informed neural networks and the well-known performance of Kalman filters to find parameters in a continuous-time system with noisy measurements. In this way, available system knowledge is used and improved to achieve a more accurate model. We show that the method works for complex systems by identifying the parameters of a double pendulum.

Please take the opportunity to connect and share this video with your friends and family if you find it useful.