Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
This addresses the challenge of inaccurate models in real-life nonlinear systems for engineers and scientists, representing an incremental improvement by integrating machine learning with existing physics-based methods.
The paper tackles the problem of model-form error in nonlinear dynamical systems by proposing a gray-box modeling approach that identifies and corrects errors in approximate governing equations, resulting in improved predictive capability and reliable state estimates across four case studies.
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduced model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using duel Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system's states.