arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01587eess.SYcs.SY
收藏

电动汽车电池放电建模：一种混合物理基础残差学习方法

Battery Discharge Modeling for Electric Vehicles: A Hybrid Physics-based Residual Learning Approach

Cornell University（康奈尔大学）

Praharshitha Aryasomayajula, Ting Bai, Andreas A. Malikopoulos

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了一种混合物理基础残差学习方法，用于提高电动汽车电池放电建模的准确性，通过结合物理模型和神经网络残差学习，有效降低误差并保持物理可解释性。

摘要：

电动汽车车队日益融入交通运输服务和能源系统，需要准确建模电池放电和荷电状态（SoC）演变，以确保车辆可靠运行和电网协调。现有方法在可解释但简化的物理基础模型和需要大量数据集的数据驱动方法之间存在权衡。本文提出了一种混合物理基础残差学习框架用于电动汽车电池放电建模。基于力平衡方程的车辆动力学模型提供了一个可解释的基线估计，捕捉空气阻力、滚动阻力和再生制动。然后，一个神经网络残差学习器纠正由复杂因素如交通状况和驾驶行为引起的偏差。实验结果表明，在1500个行程场景中，所提出的方法将平均绝对百分比误差降低到约0.8%，显著优于仅物理模型的方法，同时保持物理可解释性和计算效率。

英文摘要：

The growing integration of electric vehicle (EV) fleets into transportation services and energy systems requires accurate modeling of battery discharge and state-of-charge (SoC) evolution to ensure reliable vehicle operation and grid coordination. Existing approaches face a trade-off between interpretable but simplified physics-based models and data-driven methods that demand large datasets and may lack physical consistency. In this paper, we propose a hybrid physics-based residual learning framework for EV battery discharge modeling. A vehicle dynamics model based on force-balance equations provides an interpretable baseline estimate of energy consumption and SoC evolution, capturing aerodynamic drag, rolling resistance, and regenerative braking. A neural network residual learner then corrects discrepancies caused by complex factors such as traffic conditions and driver behavior. Experimental results on $1,500$ trip scenarios demonstrate that the proposed approach reduces the mean absolute percentage error to approximately $0.8\%$, significantly outperforming physics-only models while preserving physical interpretability and computational efficiency.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑