• Home
  • Search
  • Rapid Inverse Parameter Inference Using Physics-Informed Neural Networks
  • https://doi.org/10.1149/ma2024-012345mtgabsCopy DOI Icon

Rapid Inverse Parameter Inference Using Physics-Informed Neural Networks

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

As Li-ion batteries become more essential in today's economy, tools need to be developed to accurately and rapidly diagnose a battery's internal state-of-health. Using a Li-ion battery's (high-rate) voltage response, it is proposed to determine a battery's internal state through Bayesian calibration.However, Bayesian calibration is notoriously slow and requires thousands of model runs. To accelerate parameter inference using Bayesian calibration, a surrogate model is developed to replace the underlying physics-based Li-ion model. Developing a surrogate model for rapid Bayesian calibration analysis is discussed for both the single particle model (SPM) and the pseudo two-dimensional (P2D) model.Surrogate models are constructed using physics-informed neural networks (PINNs) that encode the influence of internal properties on observed voltage responses. In practice, a neural network can be trained by: 1) using simulation results of the physics-based model (i.e., a data-loss approach); 2) using the residuals of the governing equations themselves (i.e., a physics-loss approach); or 3) using a combination of simulation results and governing equation residuals. In the present work, PINNs are developed using a variety of training losses and neural network architectures. In this analysis, it is shown that a PINN surrogate model can be reliably trained with only physics-informed loss. However, using a coupled data-informed and physics-loss approach produced the most accurate PINNs. Figure~\\ref{fig:spm_2d} illustrates the absolute relative errors of trained PINN networks using several different training losses and neural network architectures.After determining a consistent training strategy for both the SPM and P2D PINN surrogate models, the PINNs are extended to determine additional internal state-of-health parameters. As more and more parameters were introduced, the PINN training suffered from ``the curse of dimensionality", which was mitigated by using a hierarchical training approach (where a PINN trained with fewer variable model parameters was used to train a PINN with more variable model parameters).Next, the high-dimensionality PINN surrogates are then integrated into Bayesian calibration schemes to identify internal Li-ion battery properties from experimentally measured voltages. Interpreting the high-dimensional parameter posteriors is discussed with respect to model error, parameter prior choices, and experimental errors. Figure 1

Similar Papers
  • PDF
  • Research Article
  • Citations105

Hybrid Modeling of Lithium-Ion Battery: Physics-Informed Neural Network for Battery State Estimation

  • May 30, 2023
  • Batteries
  • Soumya Singh +3
  • Research Article
  • Citations40

Surrogate modeling of parameterized multi-dimensional premixed combustion with physics-informed neural networks for rapid exploration of design space

  • Sep 29, 2023
  • Combustion and Flame
  • Kai Liu +6
  • Conference Article

Advancing Multiphase Flow Measurement: Machine Learning Vs. Traditional MPFM in Flow Loop Testing

  • Oct 13, 2025
  • Hao Jin +1
  • Research Article
  • Citations7

Physics-informed neural networks for physiological signal processing and modeling: a narrative review

  • Jul 30, 2025
  • Physiological Measurement
  • Anni Zhao +2
  • Research Article
  • Citations28

Identifying optimal architectures of physics-informed neural networks by evolutionary strategy

  • Jul 26, 2023
  • Applied Soft Computing
  • Ana Kaplarević-Mališić +6
  • Dissertation

3D Concrete Printing Material Prediction and Flow Simulation Using Physics-Informed Neural Network

  • May 01, 2024
  • Tianjie Zhang
  • Research Article
  • Citations16

1-D coupled surface flow and transport equations revisited via the physics-informed neural network approach

  • Aug 23, 2023
  • Journal of Hydrology
  • Jie Niu +4
  • Research Article
  • Citations236

A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations

  • Jan 04, 2022
  • Computer Methods in Applied Mechanics and Engineering
  • Revanth Mattey +1
  • Research Article

Physics-informed neural networks (PINNs) for the in-situ assessment of R-values, training and validation on synthetic data

  • Nov 01, 2025
  • IOP Conference Series: Earth and Environmental Science
  • A Benz +3
  • Research Article
  • Citations76

Inverse Dirichlet weighting enables reliable training of physics informed neural networks

  • Feb 15, 2022
  • Machine Learning: Science and Technology
  • Suryanarayana Maddu +3
  • Research Article
  • Citations1

Physics-informed neural networks based on source term decoupled and its application in discharge plasma simulation

  • Jan 01, 2024
  • Acta Physica Sinica
  • Ze Fang +3
  • Research Article
  • Citations42

Physics-Informed Neural Network surrogate model for bypassing Blade Element Momentum theory in wind turbine aerodynamic load estimation

  • Feb 10, 2024
  • Renewable Energy
  • Shubham Baisthakur +1
  • Research Article
  • Citations63

Indoor airflow field reconstruction using physics-informed neural network

  • Jun 28, 2023
  • Building and Environment
  • Chenghao Wei +1
  • Research Article
  • Citations4

Physics-informed neural networks in water and wastewater systems: a critical review.

  • Apr 01, 2026
  • Water research
  • Antonino Di Bella +3
  • Research Article
  • Citations10

Self-adaptive and time divide-and-conquer physics-informed neural networks for two-phase flow simulations using interface tracking methods

  • Jul 01, 2024
  • Physics of Fluids
  • Wen Zhou +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.