Physics-Informed Neural Networks for Prognostics and Health Management of Lithium-Ion Batteries
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
For Prognostics and Health Management (PHM) of Lithium-ion (Li-ion) batteries, many models have been established to characterize their degradation process. The existing empirical or physical models can reveal important information regarding the degradation dynamics. However, there are no general and flexible methods to fuse the information represented by those models. Physics-Informed Neural Network (PINN) is an efficient tool to fuse empirical or physical dynamic models with data-driven models. To take full advantage of various information sources, we propose a model fusion scheme based on PINN. It is implemented by developing a semi-empirical semi-physical Partial Differential Equation (PDE) to model the degradation dynamics of Li-ion batteries. When there is little prior knowledge about the dynamics, we leverage the data-driven Deep Hidden Physics Model (DeepHPM) to discover the underlying governing dynamic models. The uncovered dynamics information is then fused with that mined by the surrogate neural network in the PINN framework. Moreover, an uncertainty-based adaptive weighting method is employed to balance the multiple learning tasks when training the PINN. The proposed methods are verified on a public dataset of Li-ion Phosphate (LFP)/graphite batteries.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 1×
“We construct an NN as a function approximator [44] to fill this gap beyond a particular family of basis functions [26], Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodRaissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384 · cited 2×
“With this NN solver, the direct access or approximations to the involved partial derivatives are unnecessary [25], [31].”
MethodPhysics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718
Modeling of Lithium-Ion Battery Degradation for Cell Life Assessment
Xu, B., Oudalov, A., Ulbig, A., Andersson, G., & Kirschen, D. S. (2018) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2016.2578950 · Cited by 1,162
Li, J., Adewuyi, K., Lotfi, N., Landers, R. G., & Park, J. (2018) · Applied Energy · doi:10.1016/j.apenergy.2018.01.011 · Cited by 623 · cited 4×
“For instance, based on SEI formation and the growth process on both the initial and cracked surface [18], [19], (3) can be specified as where t l represents the monitoring time earlier than t k and Θ = { θ 1 , θ 2 , . . . , θ 6 } are composite parameters.”
BackgroundMethodInfluentialBattery cycle life prediction with coupled chemical degradation and fatigue mechanics
Deshpande, R., Verbrugge, M., Cheng, Y.-T., Wang, J., & Liu, P. (2012) · Journal of The Electrochemical Society · doi:10.1149/2.049210jes · Cited by 389 · cited 4×
“For instance, based on SEI formation and the growth process on both the initial and cracked surface [18], [19], (3) can be specified as where t l represents the monitoring time earlier than t k and Θ = { θ 1 , θ 2 , . . . , θ 6 } are composite parameters.”
BackgroundMethodInfluential
Research works printed but not linked: 47
- 10.1109/TIV.2018.2843126 · DOI
- 10.1109/TIV.2021.3131944 · DOI
- 10.1109/TR.2014.2299152 · DOI · Paper page
- 10.1109/TII.2020.2991454 · DOI
- 10.1109/TIV.2020.2973551 · DOI
- 10.1016/j.microrel.2016.04.002 · DOI
- 10.1016/j.asoc.2016.03.013 · DOI · Paper page
- 10.1016/j.jclepro.2018.12.041 · DOI
- Shaier, 2022, Data-driven approaches for predicting spread of infectious diseases through DINNs: Disease informed neural networks, 9, 71
- 10.1109/TPEL.2022.3176468 · DOI · Paper page
- 10.1109/TPEL.2020.3024914 · DOI · Paper page
- 10.1109/TII.2021.3105537 · doi:10.1109/tii.2021.3105537
- 10.1109/TII.2021.3089333 · DOI
- 10.1109/TIM.2013.2276473 · DOI
- 10.1016/j.jpowsour.2016.07.036 · DOI · Paper page
- 10.1109/TIE.2021.3127035 · DOI
- 10.1016/j.energy.2019.01.083 · DOI · Paper page
- Long, 2018, PDE-Net: Learning PDEs from data, 3208
- 10.1016/j.jcp.2019.108925 · DOI · Paper page
- Raissi, 2018, Deep hidden physics models: Deep learning of nonlinear partial differential equations, J. Mach. Learn. Res., 19, 932
- 10.1155/2021/9937846 · DOI
- Sherstinsky, 2018, Deriving the recurrent neural network definition and RNN unrolling using signal processing, 31, 4
- 10.36001/ijphm.2020.v11i1.2594 · DOI
- 10.1016/j.compind.2020.103386 · DOI
- 10.1016/j.jcp.2019.05.024 · DOI · Paper page
- 10.1017/cbo9780511995569 · DOI
- 10.1016/j.ymssp.2022.109347 · DOI · Paper page
- 10.1109/TIV.2020.3032642 · doi:10.1109/tiv.2020.3032642
- 10.1016/j.energy.2021.120114 · DOI · Paper page
- 10.1109/TIM.2016.2622838 · DOI · Paper page
- 10.1016/S0378-7753(02)00490-1 · DOI · Paper page
- 10.1016/j.ress.2020.107241 · DOI
- 10.1016/j.est.2020.101342 · DOI
- 10.1038/s41560-019-0356-8 · DOI · Paper page
- 10.1109/TIM.2021.3054429 · DOI
- 10.1109/TASE.2013.2250282 · DOI · Paper page
- 10.1109/JIOT.2021.3055977 · DOI
- Baydin, 2018, Automatic differentiation in machine learning: A survey, J. Mach. Learn. Res., 18, 1
- 10.1016/j.cma.2022.114823 · DOI · Paper page
- Kendall, 2018, Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, 7482
- 10.1137/20M1318043 · DOI · Paper page
- 10.1109/TIE.2020.3034855 · DOI
- 10.1016/j.asoc.2021.107195 · DOI
- 10.1016/j.est.2022.104209 · DOI
- 10.1109/TII.2022.3156965 · DOI · Paper page
- 10.1016/j.apenergy.2015.08.119 · DOI · Paper page
- 10.1007/s10915-022-01939-z · DOI · Paper page
Cited by
Li, H., Zhang, Z., Li, T., & Si, X. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111120 · Cited by 374
Wang, Y., Guo, S., Cui, Y., Deng, L., Zhao, L., Li, J., & Wang, Z. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.116125 · Cited by 107
Su, L., Xu, Y., & Dong, Z. (2024) · Energy Conversion and Economics · doi:10.1049/enc2.12125 · Cited by 86
Xiong, R., He, Y., Sun, Y., Jia, Y., & Shen, W. (2025) · Journal of Energy Chemistry · doi:10.1016/j.jechem.2025.01.019 · Cited by 52
Du, Z., & Lu, R. (2025) · Batteries · doi:10.3390/batteries11060204 · Cited by 58
Metadata
- Authors
- Wen, P., Ye, Z.-S., Li, Y., Chen, S., Xie, P., & Zhao, S.
- Venue
- IEEE Transactions on Intelligent Vehicles
- Published
- 2024-01
- Volume
- 9
- Issue
- 1
- Pages
- 2276-2289
- ISSN
- 2379-8858 (ISSN-L)
- 2379-8904
- OpenAlex
- W4386737206
- Cited by
- 205
- References
- 6
- FWCI
- 14.89
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Physics-Informed Neural Networks for Prognostics and Health Management of Lithium-Ion Batteries. https://app.cochat.ai/papers/10.1109/tiv.2023.3315548
- The paper
- Wen, P., Ye, Z.-S., Li, Y., Chen, S., Xie, P., & Zhao, S. (2024). Physics-Informed Neural Networks for Prognostics and Health Management of Lithium-Ion Batteries. IEEE Transactions on Intelligent Vehicles. https://doi.org/10.1109/tiv.2023.3315548
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.