Kalman-Bucy-Informed Neural Network for System Identification

Tobias Nagel, Marco Huber

Abstract: Identifying parameters in a system of nonlinear, ordinary differential equations is vital for designing a robust controller. However, if the system is stochastic in its nature or if only noisy measurements are available, standard optimization algorithms for system identification usually fail. We present a new approach that combines the recent advances in physics-informed neural networks and the well-known achievements of Kalman filters in order to find parameters in a continuous-time system with noisy measurements. In doing so, our approach allows estimating the parameters together with the mean value and covariance matrix of the system’s state vector. We show that the method works for complex systems by identifying the parameters of a double pendulum.