journal article·2025-11Open access

A transferable physics-informed framework for battery degradation diagnosis, knee-onset detection and knee prediction

Huang Zhang, Xixi Liu, Faisal Altaf, Torsten Wik

Abstract

The techno-economic and safety concerns of battery capacity knee occurrence call for developing online knee detection and prediction methods as an advanced battery management system (BMS) function. To address this, a transferable physics-informed framework that consists of a histogram-based feature engineering method, a hybrid physics-informed model, and a fine-tuning strategy, is proposed for online battery degradation diagnosis and knee-onset detection. The hybrid model is first developed and evaluated using a scenario-aware pipeline in protocol cycling scenarios and then fine-tuned to create local models deployed in a dynamic cycling scenario. A 2D histogram-based 17-feature set is found to be the best choice in both source and target scenarios. The fine-tuning strategy is proven to be effective in improving battery degradation mode estimation and degradation phase detection performance in the target scenario. Again, a strong linear correlation was found between the identified knee-onset and knee points. As a result, advanced BMS functions, such as online degradation diagnosis and prognosis, online knee-onset detection and knee prediction, aging-aware battery classification, and second-life repurposing, can be enabled through a battery performance digital twin in the cloud. • 2D histogram features to enable online battery diagnosis and knee-onset detection. • A hybrid model for battery degradation mode estimation and phase detection. • A fine-tuning strategy to create local models for online deployment. • The method enables advanced battery management system functions in the cloud.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Reliability and Maintenance Optimization

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (60)

Show source-provided references
1. High-power electric vehicle charging: Low-carbon grid integration pathways with stationary lithium-ion battery systems and renewable generation10.1016/j.apenergy.2022.120541 ↗
2. Decarbonization potential of electrifying 50% of US light-duty vehicle sales by 203010.1038/s41467-023-42893-0 ↗
3. Battery lifetime prognostics10.1016/j.joule.2019.11.018 ↗
4. Investigation of path dependence in commercial lithium-ion cells chosen for plug-in hybrid vehicle duty cycle protocols10.1016/j.jpowsour.2010.05.058 ↗
5. Durability and reliability of EV batteries under electric utility grid operations: Impact of frequency regulation usage on cell degradation10.3390/en13102494 ↗
6. Investigation of path-dependent degradation in lithium-ion batteries10.1002/batt.202000160 ↗
7. Review and performance comparison of mechanical-chemical degradation models for lithium-ion batteries10.1149/2.0281914jes ↗
8. Modeling of lithium plating induced aging of lithium-ion batteries: Transition from linear to nonlinear aging10.1016/j.jpowsour.2017.05.110 ↗
9. Linear and nonlinear aging of lithium-ion cells investigated by electrochemical analysis and in-situ neutron diffraction10.1149/2.1271915jes ↗
10. Electrochemical modeling of linear and nonlinear aging of lithium-ion cells10.1149/1945-7111/aba44f ↗
11. Capacity plunge of lithium-ion batteries induced by electrolyte drying-out: Experimental and modeling study10.1016/j.est.2021.103013 ↗
12. Challenges and opportunities for second-life batteries: Key technologies and economy10.1016/j.rser.2023.114191 ↗
13. Algorithm to determine the knee point on capacity fade curves of lithium-ion cells10.3390/en12152910 ↗
14. Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells10.1016/j.egyai.2020.100006 ↗
15. Automated feature extraction and selection for data-driven models of rapid battery capacity fade and end of life10.1109/TII.2021.3106593 ↗
16. Accelerated fading recognition for lithium-ion batteries with Nickel-Cobalt-Manganese cathode using quantile regression method10.1016/j.apenergy.2019.113841 ↗
17. Two-stage deep learning for online prediction of knee-point in Li-ion battery capacity degradation10.1016/j.apenergy.2022.120204 ↗
18. Degradation curve prediction of lithium-ion batteries based on knee point detection algorithm and convolutional neural network10.1109/TIM.2022.3181307 ↗
19. Nonlinear aging knee-point prediction for lithium-ion batteries faced with different application scenarios10.1016/j.etran.2023.100270 ↗
20. ICFormer: A Deep Learning model for informed lithium-ion battery diagnosis and early knee detection10.1016/j.jpowsour.2023.233910 ↗
21. “Knees” in lithium-Ion battery aging trajectories10.1149/1945-7111/ac6d13 ↗
22. An electrochemical model based degradation state identification method of Lithium-ion battery for all-climate electric vehicles application10.1016/j.apenergy.2018.03.053 ↗
23. Effective and practical parameters of electrochemical Li-ion battery models for degradation diagnosis10.1016/j.est.2021.103077 ↗
24. Nondestructive diagnostics and quantification of battery aging under different degradation paths10.1016/j.jpowsour.2022.232555 ↗
25. Identification and quantification of ageing mechanisms in Li-ion batteries by Electrochemical impedance spectroscopy10.1016/j.electacta.2022.140801 ↗
26. Enabling early detection of lithium-ion battery degradation by linking electrochemical properties to equivalent circuit model parameters10.1016/j.est.2022.104213 ↗
27. Synthesize battery degradation modes via a diagnostic and prognostic model10.1016/j.jpowsour.2012.07.016 ↗
28. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning10.1038/s41467-020-15235-7 ↗
29. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
30. Degradation diagnostics for lithium ion cells10.1016/j.jpowsour.2016.12.011 ↗
31. Incremental capacity analysis and close-to-equilibrium OCV measurements to quantify capacity fade in commercial rechargeable lithium batteries10.1149/1.2221767 ↗
32. Differential voltage analyses of high-power, lithium-ion cells: 1. Technique and application10.1016/j.jpowsour.2004.07.021 ↗
33. Parametrization of physics-based battery models from input–output data: A review of methodology and current research10.1016/j.jpowsour.2021.230859 ↗
34. A comparison of methodologies for the non-invasive characterisation of commercial Li-ion cells10.1016/j.pecs.2019.01.001 ↗
35. Ageing mechanisms in lithium-ion batteries10.1016/j.jpowsour.2005.01.006 ↗
36. Identification and quantification of ageing mechanisms in Lithium-ion batteries using the EIS technique
37. IEEE Power and Energy Society, IEEE Recommended Practice for Sizing Lead-Acid Batteries for Stationary Applications, IEEE Std 485-2020 (Revision of IEEE Std 485-2010), 2020, pp. 1–69, http://dx.doi.org/10.1109/IEEESTD.2020.9103320.10.1109/IEEESTD.2020.9103320 ↗
38. Battery capacity knee-onset identification and early prediction using degradation curvature10.1016/j.jpowsour.2024.234619 ↗
39. Comprehensive study of the aging knee and second-life potential of the Nissan Leaf e+ batteries10.1016/j.jpowsour.2024.234884 ↗
40. Technical viability of battery second life: A study from the ageing perspective10.1109/TIA.2018.2801262 ↗
41. Lithium-ion battery degradation: Comprehensive cycle ageing data and analysis for commercial 21700 cells10.1016/j.jpowsour.2024.234185 ↗
42. Scenario-aware machine learning pipeline for battery lifetime prediction
43. Sensitivities of lithium-ion batteries with different capacities to overcharge/over-discharge10.1016/j.est.2022.104997 ↗
44. Deep hidden physics models: Deep learning of nonlinear partial differential equations
45. Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems10.1016/j.cma.2022.114823 ↗
46. Automatic differentiation in machine learning: a survey
47. T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.10.1145/2939672.2939785 ↗
48. Lithium-ion battery SOH estimation based on XGBoost algorithm with accuracy correction10.3390/en13040812 ↗
49. SOH estimation of lithium-ion batteries based on multi-feature deep fusion and XGBoost10.1016/j.energy.2024.132429 ↗
50. Xgboost-based remaining useful life estimation model with extended kalman particle filter for lithium-ion batteries10.3390/s22239522 ↗
51. Transfer learning for battery smarter state estimation and ageing prognostics: Recent progress, challenges, and prospects10.1016/j.adapen.2022.100117 ↗
52. Aging datasets of commercial lithium-ion batteries: A review10.1016/j.est.2024.110560 ↗
53. The challenge and opportunity of battery lifetime prediction from field data10.1016/j.joule.2021.06.005 ↗
54. T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama, Optuna: A next-generation hyperparameter optimization framework, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2623–2631.10.1145/3292500.3330701 ↗
55. Grandini · 2020
56. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis10.1038/s41467-024-48779-z ↗
57. A hybrid approach to predict battery health combined with attention-based transformer and online correction10.1016/j.est.2023.107365 ↗
58. Predictive pretrained transformer (PPT) for real-time battery health diagnostics10.1016/j.apenergy.2024.124746 ↗
59. Digital twin of electric vehicle battery systems: Comprehensive review of the use cases, requirements, and platforms10.1016/j.rser.2023.113280 ↗
60. Technoeconomic model of second-life batteries for utility-scale solar considering calendar and cycle aging10.1016/j.apenergy.2020.115127 ↗