arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.08087cs.LGphysics.chem-ph
收藏

用于锂离子电池仿真的快速且可泛化的参数嵌入神经算子

Fast and Generalizable parameter-embedded Neural Operators for Lithium-Ion Battery Simulation

Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University(电化学与电力电子系统老化、可靠性与寿命预测中心(CARL),亚琛工业大学);Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University(电力电子与电气驱动研究所(ISEA),亚琛工业大学);Department of Mechanical Engineering, Imperial College London(机械工程系,伦敦帝国理工学院);Dyson School of Design Engineering, Imperial College London(戴森设计工程学院,伦敦帝国理工学院);Vehicle Futures Hub, Imperial College London(车辆未来中心,伦敦帝国理工学院)

Amir Ali Panahi, Daniel Luder, Billy Wu, Gregory Offer, Dirk Uwe Sauer, Weihan Li

AI总结:

本文提出了一种参数嵌入傅里叶神经算子(PE-FNO)用于锂离子电池仿真,在保持高精度的同时实现了比传统求解器快约200倍的速度,并支持跨半径和扩散率的泛化,为实时电池管理提供了高效且高保真的数字孪生解决方案。

摘要:

锂离子电池的可靠数字孪生必须以亚毫秒级的速度实现高物理保真度。在这项工作中,我们对单粒子模型(SPM)的三种算子学习代理模型进行了基准测试:深度算子网络(DeepONets)、傅里叶神经算子(FNOs)以及一种新提出的参数嵌入傅里叶神经算子(PE-FNO),该算子根据粒子半径和固相扩散率对每个谱层进行条件化。模型在涵盖四种电流系列(恒定、三角、脉冲列和高斯随机场)以及全范围荷电状态(SOC,0%至100%)的模拟轨迹上进行训练。DeepONet能准确复现恒流行为,但在更动态的负载下表现不佳。基础FNO保持网格不变性,并将浓度误差控制在1%以下,在所有负载类型下电压平均绝对误差低于1.7 mV。引入参数嵌入会略微增加误差,但能够泛化到不同的半径和扩散率。PE-FNO的执行速度比16线程SPM求解器快约200倍。因此,本文在采用贝叶斯优化的参数估计任务中探索了PE-FNO在逆任务中的能力,分别以1.14%和8.4%的平均绝对百分比误差恢复了阳极和阴极的扩散率,且与经典方法相比误差仅高出0.5918个百分点。这些结果为神经算子满足实时电池管理、实验设计和大规模推断在准确性、速度和参数灵活性方面的需求铺平了道路。PE-FNO优于传统的神经代理模型,为实现高速和高保真度的电化学数字孪生提供了一条实用路径。

英文摘要:

Reliable digital twins of lithium-ion batteries must achieve high physical fidelity with sub-millisecond speed. In this work, we benchmark three operator-learning surrogates for the Single Particle Model (SPM): Deep Operator Networks (DeepONets), Fourier Neural Operators (FNOs) and a newly proposed parameter-embedded Fourier Neural Operator (PE-FNO), which conditions each spectral layer on particle radius and solid-phase diffusivity. Models are trained on simulated trajectories spanning four current families (constant, triangular, pulse-train, and Gaussian-random-field) and a full range of State-of-Charge (SOC) (0 % to 100 %). DeepONet accurately replicates constant-current behaviour but struggles with more dynamic loads. The basic FNO maintains mesh invariance and keeps concentration errors below 1 %, with voltage mean-absolute errors under 1.7 mV across all load types. Introducing parameter embedding marginally increases error, but enables generalisation to varying radii and diffusivities. PE-FNO executes approximately 200 times faster than a 16-thread SPM solver. Consequently, PE-FNO's capabilities in inverse tasks are explored in a parameter estimation task with Bayesian optimisation, recovering anode and cathode diffusivities with 1.14 % and 8.4 % mean absolute percentage error, respectively, and 0.5918 percentage points higher error in comparison with classical methods. These results pave the way for neural operators to meet the accuracy, speed and parametric flexibility demands of real-time battery management, design-of-experiments and large-scale inference. PE-FNO outperforms conventional neural surrogates, offering a practical path towards high-speed and high-fidelity electrochemical digital twins.

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。

↑