Neural posterior estimation for scalable and accurate inverse parameter inference in Li-ion batteries

2026-04-02

AI Summary

This study addresses the high computational cost of Bayesian calibration for high-dimensional (6–27 dimensional) lithium-ion battery parameters, which hinders real-time applications. The authors propose a fast inference method based on Neural Posterior Estimation (NPE), shifting the computational burden to an offline training phase and enabling millisecond-level online parameter estimation. This work presents the first validation of NPE in high-dimensional battery parameter spaces, integrating physics-based models with fast-charging experimental data and demonstrating accuracy in estimating critical metrics such as lithium inventory loss and active material degradation. Compared to conventional Bayesian calibration, NPE achieves several orders of magnitude faster inference while maintaining or improving estimation accuracy, significantly enhancing real-time battery health management capabilities. The implementation code has been made publicly available.

Abstract

Diagnosing the internal state of Li-ion batteries is critical for battery research, operation of real-world systems, and prognostic evaluation of remaining lifetime. By using physics-based models to perform probabilistic parameter estimation via Bayesian calibration, diagnostics can account for the uncertainty due to model fitness, data noise, and the observability of any given parameter. However, Bayesian calibration in Li-ion batteries using electrochemical data is computationally intensive even when using a fast surrogate in place of physics-based models, requiring many thousands of model evaluations. A fully amortized alternative is neural posterior estimation (NPE). NPE shifts the computational burden from the parameter estimation step to data generation and model training, reducing the parameter estimation time from minutes to milliseconds, enabling real-time applications. The present work shows that NPE calibrates parameters equally or more accurately than Bayesian calibration, and we demonstrate that the higher computational costs for data generation are tractable even in high-dimensional cases (ranging from 6 to 27 estimated parameters), but the NPE method can lead to higher voltage prediction errors. The NPE method also offers several interpretability advantages over Bayesian calibration, such as local parameter sensitivity to specific regions of the voltage curve. The NPE method is demonstrated using an experimental fast charge dataset, with parameter estimates validated against measurements of loss of lithium inventory and loss of active material. The implementation is made available in a companion repository (https://github.com/NatLabRockies/BatFIT).

Problem

• inverse parameter inference
• Li-ion batteries
• Bayesian calibration
• neural posterior estimation
• real-time diagnostics

Innovation

• Neural Posterior Estimation
• Bayesian calibration
• Li-ion battery diagnostics
• Amortized inference
• Parameter estimation