journal article·2024-11Open access

Gaussian process-based online health monitoring and fault analysis of lithium-ion battery systems from field data

Joachim Schaeffer, Eric Lenz, Duncan Gulla, Martin Z. Bazant, Richard D. Braatz, Rolf Findeisen

Cell Reports Physical Science· Volume 5· Issue 11

Abstract

Health monitoring, fault analysis, and detection methods are important to operate battery systems safely. We apply Gaussian process resistance models on lithium-iron-phosphate (LFP) battery field data to separate the time-dependent and operating-point-dependent resistances. The dataset contains 28 battery systems returned to the manufacturer for warranty, each with eight cells in series, totaling 224 cells and 133 million data rows. We develop probabilistic fault detection rules using recursive spatiotemporal Gaussian processes. These processes scale linearly with the number of data points, allowing online monitoring. The fault analysis underlines that often, only a single cell shows abnormal behavior or a knee point, consistent with weakest-link failure for cells connected in series, amplified by local resistive heating. The results further the understanding of how battery packs degrade and fail in the field and demonstrate the potential of online monitoring. We open source the code and publish the dataset with this article.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Fault Detection and Control Systems · Advancements in Battery Materials

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

References (70)

Show source-provided references
1. The development and future of lithium ion batteries10.1149/2.0251701jes ↗
2. European Union (2023). Regulation
3. (eu) 2023/1542 of the european parliament and of the council of 12 july 2023 concerning concerning batteries and waste batteries, amending directive 2008/98/ec and regulation
4. (eu) 2019/1020 and repealing directive 2006/66/ec. O.J. L 191/1 66, 1-117. https://eur-lex.europa.eu/eli/reg/2023/1542/oj.
5. Hanicke · 2023
6. A review of battery fires in electric vehicles10.1007/s10694-019-00944-3 ↗
7. Social construction of fire accidents in battery energy storage systems in korea
8. Hu, W. (2023). How New York plans to regulate e-bikes in the wake of deadly fires. The New York Times. September 15, 2023. https://www.nytimes.com/article/ebike-laws-nyc.html.
9. The challenge and opportunity of battery lifetime prediction from field data10.1016/j.joule.2021.06.005 ↗
10. Plett · 2015 · 2
11. Digital twin for battery systems: Cloud battery management system with online state-of-charge and state-of-health estimation
12. Analysis and key findings from real-world electric vehicle field data10.1016/j.joule.2023.07.018 ↗
13. Principles of the battery data genome10.1016/j.joule.2022.08.008 ↗
14. Cycle life prediction for lithium-ion batteries: Machine learning and more
15. Dynamic models of li-ion batteries for diagnosis and operation: A review and perspective10.1149/2.1061814jes ↗
16. Modeling and simulation of lithium-ion batteries from a systems engineering perspective10.1149/2.018203jes ↗
17. Development of an empirical aging model for li-ion batteries and application to assess the impact of vehicle-to-grid strategies on battery lifetime10.1016/j.apenergy.2016.03.119 ↗
18. Empirical modeling of lithium-ion batteries based on electrochemical impedance spectroscopy tests10.1016/j.electacta.2015.02.021 ↗
19. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
20. Impedance-based forecasting of lithium-ion battery performance amid uneven usage10.1038/s41467-022-32422-w ↗
21. Machine learning benchmarks for the classification of equivalent circuit models from solid-state electrochemical impedance spectra10.1149/1945-7111/acd8fb ↗
22. Interpretation of high-dimensional linear regression: Effects of nullspace and regularization demonstrated on battery data10.1016/j.compchemeng.2023.108471 ↗
23. Gaussian process regression for forecasting battery state of health10.1016/j.jpowsour.2017.05.004 ↗
24. Gaussian process regression for in situ capacity estimation of lithium-ion batteries10.1109/TII.2018.2794997 ↗
25. Porous-electrode theory with battery applications10.1002/aic.690210103 ↗
26. Modeling of galvanostatic charge and discharge of the lithium/polymer/insertion cell10.1149/1.2221597 ↗
27. Review of simplified Pseudo-two-Dimensional models of lithium-ion batteries10.1016/j.jpowsour.2016.07.036 ↗
28. Perspective—Combining physics and machine learning to predict battery lifetime10.1149/1945-7111/abec55 ↗
29. Hybrid physics-informed neural networks for lithium-ion battery modeling and prognosis10.1016/j.jpowsour.2021.230526 ↗
30. Predicting battery end of life from solar off-grid system field data using machine learning10.1016/j.joule.2021.11.006 ↗
31. Advanced fault diagnosis for lithium-ion battery systems: A review of fault mechanisms, fault features, and diagnosis procedures10.1109/MIE.2020.2964814 ↗
32. A review of lithium ion battery failure mechanisms and fire prevention strategies10.1016/j.pecs.2019.03.002 ↗
33. A review of lithium-ion battery fault diagnostic algorithms: Current progress and future challenges10.3390/a13030062 ↗
34. Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data10.1016/j.energy.2021.121266 ↗
35. Online multi-fault detection and diagnosis for battery packs in electric vehicles10.1016/j.apenergy.2019.114170 ↗
36. A novel fault diagnosis method for lithium-ion battery packs of electric vehicles10.1016/j.measurement.2017.11.034 ↗
37. Lithium-ion batteries fault diagnostic for electric vehicles using sample entropy analysis method
38. Model-based fault diagnosis approach on external short circuit of lithium-ion battery used in electric vehicles10.1016/j.apenergy.2016.10.026 ↗
39. Multi-fault detection and isolation for lithium-ion battery systems10.1109/TPEL.2021.3098445 ↗
40. Modeling and simulation of high energy density lithium-ion battery for multiple fault detection10.1038/s41598-022-13771-4 ↗
41. Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods10.1016/j.apenergy.2017.05.139 ↗
42. Machine learning-based data-driven fault detection/diagnosis of lithium-ion battery: A critical review10.3390/electronics10111309 ↗
43. Data-driven fault diagnosis in battery systems through cross-cell monitoring10.1109/JSEN.2020.3017812 ↗
44. Data-driven prediction of battery failure for electric vehicles10.1016/j.isci.2022.104172 ↗
45. Towards a smarter battery management system: A critical review on battery state of health monitoring methods10.1016/j.jpowsour.2018.10.019 ↗
46. Critical review of state of health estimation methods of li-ion batteries for real applications10.1016/j.rser.2015.11.042 ↗
47. Review—“knees” in lithium-ion battery aging trajectories10.1149/1945-7111/ac6d13 ↗
48. Spatiotemporal learning via infinite-dimensional Bayesian filtering and smoothing: A look at Gaussian process regression through Kalman filtering10.1109/MSP.2013.2246292 ↗
49. Recursive Gaussian process: On-line regression and learning10.1016/j.patrec.2014.03.004 ↗
50. Learning battery model parameter dynamics from data with recursive gaussian process regression
51. Multi-year field measurements of home storage systems and their use in capacity estimation
52. Inhomogeneities and cell-to-cell variations in lithium-ion batteries, a review10.3390/en14113276 ↗
53. Exploring the effects of cell-to-cell variability on battery aging through stochastic simulation techniques
54. Williams · 2006 · 2
55. DC internal resistance during charge: Analysis and study on LiFePO 4batteries
56. Duvenaud · 2014
57. Theory of coherent nucleation in phase-separating nanoparticles10.1021/nl400497t ↗
58. Phase transformation dynamics in porous battery electrodes10.1016/j.electacta.2014.08.083 ↗
59. Unification of internal resistance estimation methods for li-ion batteries using hysteresis-free equivalent circuit models10.3390/batteries6020032 ↗
60. Pulse resistance based online temperature estimation for lithium-ion cells10.1016/j.jpowsour.2021.229523 ↗
61. Charge transfer kinetics at the solid–solid interface in porous electrodes10.1038/ncomms4585 ↗
62. Unified quantum theory of electrochemical kinetics by coupled ion–electron transfer10.1039/D3FD00108C ↗
63. Estimates of location based on rank tests10.1214/aoms/1177704172 ↗
64. Gumbel · 1958
65. Limiting forms of the frequency distribution of the largest or smallest member of a sample10.1017/S0305004100015681 ↗
66. Lifetime of high-k gate dielectrics and analogy with strength of quasibrittle structures10.1063/1.3256225 ↗
67. Internal resistance matching for parallel-connected lithium-ion cells and impacts on battery pack cycle life10.1016/j.jpowsour.2013.11.101 ↗
68. Cycle life analysis of series connected lithium-ion batteries with temperature difference10.1016/j.jpowsour.2014.04.034 ↗
69. Solin · 2016
70. Särkkä · 2019