English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bayesian parameter inference is useful to improve Li-ion battery diagnosticsand can help formulate battery aging models. However, it is computationallyintensive and cannot be easily repeated for multiple cycles, multiple operatingconditions, or multiple replicate cells. To reduce the computational cost ofBayesian calibration, numerical solvers for physics-based models can bereplaced with faster surrogates. A physics-informed neural network (PINN) isdeveloped as a surrogate for the pseudo-2D (P2D) battery model calibration. Forthe P2D surrogate, additional training regularization was needed as compared tothe PINN single-particle model (SPM) developed in Part I. Both the PINN SPM andP2D surrogate models are exercised for parameter inference and compared to dataobtained from a direct numerical solution of the governing equations. Aparameter inference study highlights the ability to use these PINNs tocalibrate scaling parameters for the cathode Li diffusion and the anodeexchange current density. By realizing computational speed-ups of 2250x for theP2D model, as compared to using standard integrating methods, the PINNsurrogates enable rapid state-of-health diagnostics. In the low-dataavailability scenario, the testing error was estimated to 2mV for the SPMsurrogate and 10mV for the P2D surrogate which could be mitigated withadditional data.

PINN surrogate of Li-ion battery models for parameter inference. Part II: Regularization and application of the pseudo-2D model