发表机构
Lanzhou University of Technology; Hiroshima University; Nanjing University - Suzhou Campus; Princeton University（兰州理工大学; 广岛大学; 南京大学苏州校区; 普林斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对工业降阶建模中的自相交轨迹问题，提出LA-NODEs框架，经理论分析与IPMSM、DES两类工业模型验证，可提升建模精度与保真度，为复杂工业系统高精度数据驱动建模提供有效方法。
AI 中文摘要
本文针对工业降阶建模中出现的（相空间内）自相交轨迹问题，提出了隐变量增强型神经常微分方程（Latent-Augmented Neural Ordinary Differential Equations，LA-NODEs）框架。从人工智能视角，该方法对传统神经常微分方程进行增强以提升模型表达能力，能够表示降阶系统中可能出现的冲突向量场，从而提高学习精度。通过理论分析，明确了该框架的内在机制，并推导了确定所需最小增强维度的条件。从工程应用视角，在两个代表性工业模型的降阶系统上验证了所提方法的有效性，即内置式永磁同步电机（Interior Permanent Magnet Synchronous Motor，IPMSM）驱动系统与分布式能源系统（Distributed Energy System，DES）。实验结果表明，该方法可恢复传统方法难以捕捉的系统特征，在预测精度与建模保真度方面实现了更优性能，为复杂工业系统的高精度数据驱动建模提供了有效途径。
英文摘要
This paper addresses the issue of self-intersecting trajectories (in phase space) in industrial reduced-order modeling and proposes the Latent-Augmented Neural Ordinary Differential Equations (LA-NODEs) framework. From the perspective of artificial intelligence, the proposed method augments conventional neural ordinary differential equations to enhance model expressiveness, enabling the representation of conflicting vector fields that may arise in reduced-order systems, thereby improving learning accuracy. Through theoretical analysis, the underlying mechanism of the framework is established, and a condition for determining the minimum required augmentation dimension is derived. From the perspective of engineering applications, the effectiveness of the proposed method is validated on the reduced-order system of two representative industrial models, namely an interior permanent magnet synchronous motor (IPMSM) drive and a distributed energy system (DES). Experimental results demonstrate that the proposed method can recover system features that are difficult to capture using conventional approaches and achieve superior performance in terms of prediction accuracy and modeling fidelity, thereby providing an effective approach for high-precision data-driven modeling of complex industrial systems.
