DiffLiB: High-fidelity differentiable modeling of lithium-ion batteries and efficient gradient-based parameter identification

2025-04-29

AI Summary

Inverse identification of parameters in the Doyle–Fuller–Newman (DFN) model for lithium-ion batteries has long been hindered by strong nonlinearity, time dependence, and multiscale dynamics, impeding industrial deployment. To address this, we propose DiffLiB—a high-fidelity, differentiable finite element simulation framework—featuring the first custom automatic differentiation rules and an adjoint-based implicit differentiation method specifically designed for the DFN model, enabling end-to-end differentiable modeling. Leveraging finite element discretization, vector-Jacobian product (VJP) structural optimization, and gradient-driven optimization, DiffLiB achieves forward prediction accuracy comparable to COMSOL (terminal voltage RMSE < 2 mV) while reducing the number of forward solves required for parameter identification by 96% compared to gradient-free methods, yielding a 72% overall speedup. This work establishes a new paradigm for differentiable electrochemical modeling and efficient parameter estimation.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The physics-based Doyle-Fuller-Newman (DFN) model, widely adopted for its precise electrochemical modeling, stands out among various simulation models of lithium-ion batteries (LIBs). Although the DFN model is powerful in forward predictive analysis, the inverse identification of its model parameters has remained a long-standing challenge. The numerous unknown parameters associated with the nonlinear, time-dependent, and multi-scale DFN model are extremely difficult to be determined accurately and efficiently, hindering the practical use of such battery simulation models in industrial applications. To tackle this challenge, we introduce DiffLiB, a high-fidelity finite-element-based LIB simulation framework, equipped with advanced differentiable programming techniques so that efficient gradient-based inverse parameter identification is enabled. Customized automatic differentiation rules are defined by identifying the VJP (vector-Jacobian product) structure in the chain rule and implemented using adjoint-based implicit differentiation methods. Four numerical examples, including both 2D and 3D forward predictions and inverse parameter identification, are presented to validate the accuracy and computational efficiency of DiffLiB. Benchmarking against COMSOL demonstrates excellent agreement in forward predictions, with terminal voltage discrepancies maintaining a root-mean-square error (RMSE) below 2 mV across all test conditions. In parameter identification tasks using experimentally measured voltage data, the proposed gradient-based optimization scheme achieves superior computational performance, with 96% fewer forward predictions and 72% less computational time compared with gradient-free approaches. These results demonstrate that DiffLiB is a versatile and powerful computational framework for the development of advanced LIBs.

Problem

• Inverse identification of DFN model parameters is challenging
• Efficient gradient-based parameter identification for LIBs is needed
• Nonlinear, time-dependent DFN model parameters are hard to determine

Innovation

• Differentiable programming for gradient-based parameter identification
• Adjoint-based implicit differentiation methods implementation
• High-fidelity finite-element-based LIB simulation framework