Probabilistic machine learning based predictive and interpretable digital twin for dynamical systems. (June 2023)

• Record Type: Journal Article
• Authors: Tripura, Tapas; Desai, Aarya Sheetal; Adhikari, Sondipon; Chakraborty, Souvik
• Is Part Of: Computers & structures. Volume 281(2023)
• Publication Date: 2023-06
• Subjects: Predictive digital twin -- Model update -- Probabilistic machine learning -- Stochastic differential equation; Structural engineering -- Data processing -- Periodicals; Electronic data processing -- Structures, Theory of -- Periodicals; 624.171
• DOI: 10.1016/j.compstruc.2023.107008
• Languages: English
• ISSNs: 0045-7949

Abstract

Highlights: A framework for creating and updating digital twins for dynamical systems is proposed. A library of candidate functions is used to infer perturbation in the existing digital twin model. The framework can work with both input–output and output-only observations. Highly nonlinear dynamical systems such as the crack-degradation problem are considered. The proposed framework provides an exact and explainable description of the perturbations. Abstract: A framework for creating and updating digital twins for dynamical systems from a library of physics-based functions is proposed. The sparse Bayesian machine learning is used to update and derive an interpretable expression for the digital twin. Two approaches for updating the digital twin are proposed. The first approach makes use of both the input and output information from a dynamical system, whereas the second approach utilizes output-only observations to update the digital twin. Both methods use a library of candidate functions representing certain physics to infer new perturbation terms in the existing digital twin model. In both cases, the resulting expressions of updated digital twins are identical, and in addition, the epistemic uncertainties are quantified. In the first approach, the regression problem is derived from a state-space model, whereas in the latter case, the output-only information is treated as a stochastic process. The concepts of Itô calculus and Kramers-Moyal expansion are being utilized to derive the regression equation. The performance of the proposed approaches is demonstrated using highly nonlinear dynamical systems such as the crack-degradation problem. Numerical results demonstrated in this paper almost exactly identify the correct perturbation terms along with their associated parameters in the dynamical system. The probabilistic nature of the proposed approach also helps in quantifying the uncertainties associated with updated models. The proposed approaches provide an exact and explainable description of the perturbations in digital twin models, which can be directly used for better cyber-physical integration, long-term future predictions, degradation monitoring, and model-agnostic control.