Physics-Embedded Neural ODEs for Sim2Real Edge Digital Twins of Hybrid Power Electronics Systems

TL;DR

This paper introduces Physics-Embedded Neural ODEs (PENODE) for hybrid power electronics systems, enabling accurate, interpretable, and resource-efficient edge digital twins that improve real-time monitoring and control.

Contribution

The paper presents a novel PENODE architecture that embeds hybrid dynamics and known physics into neural ODEs for improved edge deployment and generalization.

Findings

Achieves higher accuracy across various black-box scenarios.

Reduces neuron count by 75%, enhancing efficiency.

Supports FPGA deployment for real-time control.

Abstract

Edge Digital Twins (EDTs) are crucial for monitoring and control of Power Electronics Systems (PES). However, existing modeling approaches struggle to consistently capture continuously evolving hybrid dynamics that are inherent in PES, degrading Sim-to-Real generalization on resource-constrained edge devices. To address these challenges, this paper proposes a Physics-Embedded Neural ODEs (PENODE) that (i) embeds the hybrid operating mechanism as an event automaton to explicitly govern discrete switching and (ii) injects known governing ODE components directly into the neural parameterization of unmodeled dynamics. This unified design yields a differentiable end-to-end trainable architecture that preserves physical interpretability while reducing redundancy, and it supports a cloud-to-edge toolchain for efficient FPGA deployment. Experimental results demonstrate that PENODE achieves significantly higher accuracy in benchmarks in white-box, gray-box, and black-box scenarios, with a 75% reduction in neuron count, validating that the proposed PENODE maintains physical interpretability, efficient edge deployment, and real-time control enhancement.