Abstract:

This paper presents Dual Digital Twin, the next level of digital twin, in the presence of two levels of communication availability, for battery system real-time monitoring and control in electric vehicles. To implement the dual digital twin concept, an online adaptive model reduction problem is formulated with time scale differences induced by the time sensitivity property of industrial applications and limitations of infrastructure. The online adaptive battery reduced order model framework is proposed to minimize model reduction error and battery system control penalty. It uses a gated recurrent unit neural network to construct battery internal states from Internet of things sensor measurements and incremental learning techniques for data stream updates. The framework uses the Lyapunov stability theorem for physics-informed updates, enhancing synchronization with physical battery behavior. Simulations using a Li-ion battery and single particle digital twin model show a 1.70% average reduced-order model prediction error and 43.3% accuracy improvement. The method is robust against varying environmental factors and noise.