Predictive parametric inference of lithium-ion battery degradation trajectory through high-throughput physics-based simulation
Abstract
Abstract Inferring the physical parameters that govern lithium-ion battery degradation is critical for the prediction of batter lifetime, which however remains challenging owning to the complexity of physics-based models, the non-uniqueness of inverse solutions, and the experimental inaccessibility of governing parameters. Here, we develop a physics-based simulation emulator framework for predictive parametric inference of battery degradation trajectories. A neural-network emulator, trained on a dataset generated by pseudo-two-dimensional (P2D) battery simulations, allows rapid forward evaluation from parameters to degradation trajectories and thereby replaces costly repeated simulation. This high-throughput capability enables Bayesian inversion that maps experimental trajectories onto the most probable latent parameters among the candidate solutions, while incorporating physical constraints and similarities among cycling conditions. Most significantly, the inferred parametric representation provides a physics-grounded basis for forecasting complete degradation trajectories. Using only the early-life 100 − 95% state-of-health segment, our approach reduces the RMSE of late-life trajectory prediction to 59.00 cycles, in contrast with 79.62 cycles by the best data-driven approach reported. Together, these results establish an efficient route from physics-based parametric inference to practical degradation prediction, particularly where experimental data are scarce.
Read the paper
Related studies
- Preliminary Toxicity Analysis of 3DCRT versus IMRT on the High Dose Arm of the RTOG 0126 Prostate Cancer Trial
- Adaptive Radiotherapy for Head and Neck Cancer: Initial Clinical Outcomes from a Prospective Trial
- American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology
- Motion Management Strategies and Technical Issues Associated with Stereotactic Body Radiotherapy of Thoracic and Upper Abdominal Tumors: A Review from NRG Oncology
- High-dose-rate interstitial brachytherapy as a monotherapy for localized prostate cancer: treatment description and preliminary results of a phase I/II clinical trial
- Highly efficient training, refinement, and validation of a knowledge-based plan quality control system for radiotherapy clinical trials
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.