Physics-Informed Neural Network with Transfer Learning for State Estimation in Lithium-Ion Batteries using the Single Particle Model with Electrolyte

2026-06-26

AI Summary

This work addresses the limitations of conventional physics-informed neural networks (PINNs) for battery modeling—namely, slow convergence and high computational cost due to the need for retraining from scratch across different cell chemistries or operating conditions. The study introduces transfer learning into the SPMe-PINN framework for the first time, leveraging a pre-trained generic electrochemical dynamics model. By combining weight transfer, partial layer freezing, and fine-tuning strategies, the approach rapidly adapts to target cells while accurately estimating key state variables. The method substantially enhances cross-cell generalization and training efficiency, achieving high-fidelity voltage predictions with significantly reduced training time, all while preserving electrochemical consistency. Its effectiveness and robustness across multiple battery scenarios are validated using PyBaMM simulations.

Abstract

Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving nonlinear partial differential equations (PDEs), including battery electrochemical models. They typically en-force conservation laws within the loss function to ensure physically consistent solutions. Tradi-tional numerical methods such as finite difference, finite volume, and finite element techniques, re-ly on discretization and can be computationally expensive for nonlinear systems. To address this challenge, PINNs offer improved scalability, particularly for reduced-order models like the single particle model with electrolyte (SPMe). The SPMe describes lithium-ion battery dynamics through coupled diffusion, transport, reaction kinetics, and voltage equations. Despite these advantages, training SPMe-based PINNs from scratch for different battery chemistries or operating conditions is demanding and often leads to slow convergence. To overcome this limitation, this work introduces a transfer learning framework for SPMe-PINNs. The model is first pretrained to learn general elec-trochemical dynamics and then adapted to a target battery by transferring weights, freezing se-lected layers, and fine tuning the remaining parameters, including estimating key electrochemical variables. Validation using PyBaMM demonstrates accurate voltage prediction, indicating that the proposed approach preserves electrochemical consistency while reducing training time and ena-bling efficient generalization across batteries.

Problem

• Physics-Informed Neural Networks
• Transfer Learning
• State Estimation
• Lithium-Ion Batteries
• Single Particle Model with Electrolyte

Innovation

• Physics-Informed Neural Networks
• Transfer Learning
• Single Particle Model with Electrolyte
• State Estimation
• Lithium-Ion Batteries