Prognosis of Li-ion Batteries Under Large Load Variations Using Hybrid Physics-Informed Neural Networks



Published Oct 26, 2023
Kajetan Fricke Renato Nascimento Matteo Corbetta Chetan Kulkarni Felipe Viana


The development of new modes of transportation such as electric vertical takeoff and landing aircraft and the use of drones for package and medical delivery have increased the demand for reliable and powerful electric batteries. Therefore, accurately predicting the degradation of a battery’s state-ofhealth (SOH) and state-of-charge (SOC) is a crucial albeit still challenging task. There is a need for models that can accurately predict the SOH and SOC while taking into account the specific characteristics of a battery cell and its usage profile. While traditional physics-based and data-driven approaches are used to monitor the SOH and SOC, they both have limitations related to computational costs or that require engineers to continually update their prediction models as new battery cells are developed and put into use in battery-powered vehicle
Battery capacity degradation can vary from battery to battery and can also be influenced by changes in load due to internal thermal stress. While sophisticated electrochemistry-based models can provide precise predictions of the SOC during a
discharge cycle when parameters are well-tuned, using highfidelity models for prognostics purposes can be computationally expensive. Those models also require tuning to specific battery types and at times to specific specimens, thus hindering generalization. In contrast, purely data-driven approaches can learn the relationship between input and output for SOC prediction based on load input, but they require a large and diverse training dataset and lack any physical or electrochemical understanding, making far-ahead predictions challenging if test loading conditions fall outside the training distribution. To address some of the drawbacks of the aforementioned modeling approaches, in this paper, we enhance a hybrid physics-informed machine learning version of a battery SOC model we presented in previous work to predict voltage drop
during discharge. The enhanced model captures the effect of wide variation of load levels, in the form of input current,
which causes large thermal stress cycles. The cell temperature build-up during a discharge cycle is used to identify temperature-sensitive model parameters. Additionally, we enhance an existing aging model built upon cumulative energy drawn by introducing the effect of the load level. We then map cumulative energy and load level to battery capacity with a Gaussian process model. To validate our approach we use a battery aging dataset collected on a self-developed testbed, where we used a wide current level range to age battery packs in accelerated fashion. Prediction results show that our model can be successfully calibrated and generalizes across all applied load levels.

How to Cite

Fricke, K., Nascimento, R., Corbetta, M., Kulkarni, C., & Viana, F. (2023). Prognosis of Li-ion Batteries Under Large Load Variations Using Hybrid Physics-Informed Neural Networks. Annual Conference of the PHM Society, 15(1).
Abstract 814 | PDF Downloads 438



Li-Ion battery prognosis, Physics-informed machine learning

Bole, B., Kulkarni, C., & Daigle, M. (2014). Randomized battery usage data set. NASA AMES prognostics data repository, 70.
Daigle, M. J., & Kulkarni, C. S. (2013, Sep). Electrochemistrybased battery modeling for prognostics. In 2013 annual conference of the phm society (p. 13 pages). New Orleans, USA: PHM Society.
Dubarry, M., Truchot, C., & Liaw, B. Y. (2012). Synthesize battery degradation modes via a diagnostic and prognostic model. Journal of Power Sources, 219, 204--216.
Gardner, J. R., Pleiss, G., Bindel, D., Weinberger, K. Q., & Wilson, A. G. (2018). Gpytorch: Blackbox matrixmatrix gaussian process inference with gpu acceleration.
In Advances in neural information processing systems. Introduction of inr18650-25r [Computer software manual]. (2013, 10).
Karthikeyan, D. K., Sikha, G., & White, R. E. (2008). Thermodynamic model development for lithium intercalation electrodes. Journal of Power Sources, 185(2), 1398--1407.
Lutsey, N., & Nicholas, M. (2019). Update on electric vehicle costs in the united states through 2030. Int. Counc. Clean Transp, 12.
Lyu, Z., Wang, G., & Gao, R. (2021). Li-ion battery prognostic and health management through an indirect hybrid model. Journal of Energy Storage, 42, 102990.
Nascimento, R. G., Corbetta, M., Kulkarni, C. S., & Viana, F. A. C. (2021a). Hybrid physics-informed neural networks for lithium-ion battery modeling and prognosis. Journal of Power Sources, 230526. doi: 10.1016/
Nascimento, R. G., Corbetta, M., Kulkarni, C. S., & Viana, F. A. C. (2021b, Nov-Dec). Li-ion battery aging with hybrid physics-informed neural networks
and fleet-wide data. In 2020 Annual Conference of the PHM Society. Virtual Event: PHM Society.
Nascimento, R. G., Fricke, K., & Viana, F. A. C. (2020). A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural networks. Engineering Applications of Artificial Intelligence, 96,
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library.
In Advances in neural information processing systems 32 (pp. 8024--8035). Curran Associates, Inc. Retrieved from
9015-pytorch-an-imperative-style -high-performance-deep-learning
Tampier Cotoras, C., Perez, A., Jaramillo Montoya, F., Quintero, V., Orchard, M., & Silva, J. (2015, 10). Lithiumion battery end-of-discharge time estimation and prognosis based on bayesian algorithms and outer feedback correction loops: A comparative analysis..
Zhang, Y., Xiong, R., He, H., & Liu, Z. (2017). A lstmrnn method for the lithuim-ion battery remaining useful life prediction. In 2017 prognostics and system health management conference (phm-harbin) (pp. 1--4).
Technical Research Papers

Most read articles by the same author(s)

1 2 > >>