Skip to main content
QUICK REVIEW

[论文解读] PINEAPPLE: Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter Inference in Lithium-Ion Battery Electrodes

Karkulali Pugalenthi, Jian Cheng Wong|arXiv (Cornell University)|Feb 20, 2026
Advanced Battery Technologies Research被引用 0
一句话总结

PINEAPPLE 将物理信息神经网络与进化搜索结合,用于实时、零散预测,并对电压–时间数据推断循环依赖的内部状态参数,具零-shot预测能力和显著加速。

ABSTRACT

Accurate, real-time, yet non-destructive estimation of internal states in lithium-ion batteries is critical for predicting degradation, optimizing usage strategies, and extending operational lifespan. Here, we introduce PINEAPPLE (Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter inference in Lithium-ion battery Electrodes), a novel framework that integrates physics-informed neural networks (PINNs) with an evolutionary search algorithm to enable rapid, scalable, and interpretable parameter inference with potential for application to next-generation batteries. The meta-learned PINN utilizes fundamental physics principles to achieve accurate zero-shot prediction of electrode behavior with test errors below 0.1$\%$ while maintaining an order-of-magnitude speed-up over conventional solvers. PINEAPPLE demonstrates robust parameter inference solely from voltage-time discharge curves across multiple batteries from the open-source CALCE repository, recovering the evolution of key internal state parameters such as Li-ion diffusion coefficients across usage cycles. Notably, the inferred cycle-dependent evolution of these parameters exhibit consistent trends across different batteries without any customized degradation physics-embedded heuristic, highlighting the effective regularizing effect and robustness that can be conferred through incorporation of fundamental physics in PINEAPPLE. By enabling computationally efficient, real-time parameter estimation, PINEAPPLE offers a promising route towards the non-destructive, physics-based characterization of inter-cell and intra-cell variability of battery modules and battery packs, thereby unlocking new opportunities for downstream on-the-fly needs in next-generation battery management systems such as individual cell-scale state-of-health diagnostics.

研究动机与目标

  • 推动非破坏性、实时推断内部电池状态以提升预测与BMS性能。
  • 开发一个将物理模型与数据驱动学习结合的框架,以推断循环相关的内部参数。
  • 实现快速、稳健且可解释的参数推断,具有跨电池循环以及可能的不同化学体系的可扩展性。
  • 在开放的 CALCE 数据上演示该方法,以恢复扩散系数及相关内部状态趋势。

提出的方法

  • 引入 PINEAPPLE,这是一个将物理信息神经网络(PINNs)与用于 prognostic 参数推断的进化搜索相结合的框架。
  • 使用 Baldwinian 元学习策略对单粒子模型(SPM)进行通用化 LE-PINN 的预训练,以实现零-shot 预测。
  • 将循环相关的参数推断表述为对缩放因子(ηD_p, ηD_n, ηG_p, ηcmax,p)的进化搜索,这些因子调制 SPM 中的 D_p、D_n、G_p 和 c_max。
  • 通过对每个循环仅对最终层权重进行快速物理约束的闭式解(带 Tikhonov 正则化的最小二乘)进行微调。
  • 进行外层进化优化,以学习权重分布(w̃)和超参数,在跨任务的物理一致性和预测精度之间达到最大化。
  • 通过最小化观测的 V–t 曲线与 LE-PINN 输出的预测 V–t 曲线之间的错配,在 online 阶段从电压–时间数据推断内部状态参数。
Figure 1 : Discharge voltage-time (V-t) curves for the four selected CX2 batteries. A red-to-blue gradient color scheme is used to distinguish V-t curves across different cycles (CALCE CX2-34: 50–1726 cycles, CX2-36: 53–1958 cycles, CX2-37: 53–1274 cycles, CX2-38: 53–1949 cycles) during the battery’
Figure 1 : Discharge voltage-time (V-t) curves for the four selected CX2 batteries. A red-to-blue gradient color scheme is used to distinguish V-t curves across different cycles (CALCE CX2-34: 50–1726 cycles, CX2-36: 53–1958 cycles, CX2-37: 53–1274 cycles, CX2-38: 53–1949 cycles) during the battery’

实验结果

研究问题

  • RQ1是否可以利用基于 PINN 的反演方法从 V–t 数据非破坏性地推断锂离子电池的循环相关内部状态参数?
  • RQ2将物理信息通过 SP M 和 Baldwinian 元学习引入,是否能在不同 SP M 参数下实现零-shot、准确预测?
  • RQ3进化搜索是否能稳健地推断出在真实数据中对电池间差异进行正则化的关键缩放因子?
  • RQ4推断的扩散系数及相关参数在循环中是否呈现物理上可信的退化趋势?

主要发现

  • 该框架实现了零-shot 预测,在电极行为上的测试误差低于0.1%。
  • PINEAPPLE 相较于传统求解器如 PyBAMM,在相似精度下提供数量级的加速。
  • 推断的循环相关扩散系数(D_p、D_n)及几何/浓度参数(G_p、c_max,p)显示出一致、物理上可信的退化趋势,与容量衰减相关。
  • 从 CALCE 数据推断出多组 CX2 电池中锂离子扩散及相关状态的有意义演化。
  • 该方法实现了非破坏性、实时、基于物理的表征,适用于下一代电池管理系统中的单体内/外部差异性分析。
  • Baldwinian 元学习阶段产生了一个通用的 LE-PINN,能够快速适应新的物理条件并提供快速前向求解。
Figure 2 : PINEAPPLE schematic. The nonlinear hidden layers of LE-PINN are meta-learned (pre-trained) through Baldwinian neuroevolution, which takes less than 600 seconds on a sparse simulation dataset with diffusion coefficients ( $D_{k}$ ) spanning 3 orders of magnitude. The fine-tuning (forward s
Figure 2 : PINEAPPLE schematic. The nonlinear hidden layers of LE-PINN are meta-learned (pre-trained) through Baldwinian neuroevolution, which takes less than 600 seconds on a sparse simulation dataset with diffusion coefficients ( $D_{k}$ ) spanning 3 orders of magnitude. The fine-tuning (forward s

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。