基于神经常微分方程的电力变压器虚拟温度传感器
Virtual Temperature Sensors in Power Transformers Using Neural Ordinary Differential Equations
- University of Oslo（奥斯陆大学）
- SINTEF AS（辛特夫研究院）
- Norwegian University of Life Sciences（挪威生命科学大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出结合物理知识的神经常微分方程框架，利用15台不同变压器的时间序列数据，实现电力变压器热行为的鲁棒预测，解决了现有方法的局限性。
AI中文摘要：
电力变压器热行为的准确建模与预测对可靠性、资产寿命及电力系统优化运行至关重要。有限元法（FEM）和计算流体动力学（CFD）等数值方法保真度高，但计算成本高、需复杂网格生成，且在变压器几何结构未知时，通常不适用于实时或大规模应用。集总参数热模型更实用，但依赖变压器特定热常数，可能无法捕捉运行与环境条件变化下的动态响应。纯数据驱动的机器学习方法，包括人工神经网络、卷积神经网络和长短期记忆（LSTM）网络，在变压器温度预测中已取得成效，但通常需要大量高质量训练数据，且可能产生物理上不一致或不可解释的结果。本文提出一种结合物理知识的神经常微分方程（Neural ODE）框架，用于从真实世界时间序列数据预测变压器热行为。神经ODE在连续时间内建模系统动力学，提供平滑轨迹预测及连续演化热动力学的自然表示。一项关键贡献是将简化的传热方程直接整合到神经ODE公式中。该模型在来自挪威不同地区、具有不同设计和冷却机制的15台变压器数据集上进行评估。结果表明，所开发的神经ODE框架为异构变压器单元提供了一种标准化、结合物理知识且鲁棒的预测方法。
英文摘要：
Accurate modeling and forecasting of power transformer thermal behavior are critical for reliability, asset lifetime, and optimized power system operation. Numerical approaches such as finite element methods (FEM) and computational fluid dynamics (CFD) offer high fidelity but are computationally expensive, require complex mesh generation, and are often impractical for real-time or large-scale applications, particularly when transformer geometries are unknown. Lumped-parameter thermal models are more practical but depend on transformer-specific thermal constants and may fail to capture dynamic responses under varying operating and environmental conditions. Purely data-driven machine learning methods, including artificial neural networks, convolutional neural networks, and long short-term memory (LSTM) networks, have shown success in forecasting transformer temperatures but typically require large volumes of high-quality training data and may produce physically inconsistent or uninterpretable results. This paper develops a physics-aware Neural Ordinary Differential Equation (Neural ODE) framework for forecasting transformer thermal behavior from real-world time-series data. Neural ODEs model system dynamics in continuous time, providing smooth trajectory prediction and a natural representation of continuously evolving thermal dynamics. A key contribution is the integration of simplified heat-transfer equations directly into the Neural ODE formulation. The model is evaluated across datasets from fifteen transformers in different regions of Norway with varying designs and cooling mechanisms. The results demonstrate that the developed Neural ODE framework provides a standardized, physics-aware, and robust forecasting approach for heterogeneous transformer units.
