将物理机制嵌入神经微分方程，提升电力电子系统边缘数字孪生的精度与效率
Physics-Embedded Neural ODEs for Sim2Real Edge Digital Twins of Hybrid Power Electronics Systems
- 用事件自动机显式建模开关行为，将物理规律注入神经网络参数化
- 在多种场景下精度显著提升，神经元数量减少75%
- 适合需实时控制与边缘部署的电力电子系统开发者
边缘数字孪生（EDT）对电力电子系统（PES）的监控与控制至关重要。然而，现有建模方法难以持续捕捉PES固有的连续演化混合动态，在资源受限的边缘设备上导致仿真到现实的泛化能力下降。为此，本文提出物理嵌入神经微分方程（PENODE），通过（i）将混合运行机制建模为事件自动机以显式控制离散切换，（ii）将已知的微分方程组分直接注入神经网络对未建模动态的参数化中。该统一设计形成可端到端训练的可微架构，保持物理可解释性的同时减少冗余，并支持云到边的FPGA高效部署。实验表明，PENODE在白盒、灰盒和黑盒场景下的基准测试中均实现显著更高的精度，神经元数量减少75%，验证了其在保持物理可解释性、高效边缘部署和实时控制增强方面的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。