Realistic multi-fault diagnostics of millions-scale Li-ion batteries with rapid unsupervised learning
Source abstract
Abstract
The rapid deployment of battery-swapping stations necessitates scalable and reliable fault diagnosis, yet massive, sparse operational data and scarce labeled samples make this challenging. Here, we report a rapid unsupervised learning framework for realistic multi-fault diagnosis in million-scale battery fleets. Our approach employs a double-layer mechanism. First, we rapidly screen for abnormal devices by extracting features from voltage-envelope sequences. Subsequently, we pinpoint faulty cells and types using an enhanced two-stage unsupervised clustering combined with rule-based fault tracing. The framework is validated on a production dataset of over 128,000 devices, achieving 97.33% device-layer and 99.66% cell-layer accuracy. Laboratory tests on recalled batteries further confirm the detection of low-capacity and micro-short-circuit faults. These results demonstrate scalability and robustness under sparse-data conditions, enabling reliable operations for large-scale energy storage systems.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Engineering and Test Systems · VLSI and Analog Circuit Testing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. A review of equivalent-circuit model, degradation characteristics and economics of li-ion battery energy storage system for grid applications10.1016/j.est.2024.113908 ↗
2. Forecasting state-of-health of lithium-ion batteries using variational long short-term memory with transfer learning10.1016/j.est.2021.102893 ↗
3. A review of modeling, management, and applications of grid-connected li-ion battery storage systems10.1109/TSG.2022.3188598 ↗
4. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis10.1038/s41467-024-48779-z ↗
5. A data-driven auto-cnn-lstm prediction model for lithium-ion battery remaining useful life10.1109/TII.2020.3008223 ↗
6. Improving the state-of-health estimation of lithium-ion batteries based on limited labeled data10.1016/j.est.2024.113744 ↗
7. Truck-based inter-station battery transportation strategy for battery swapping stations considering the intra-day irregular behavior of electric vehicles10.1016/j.egyr.2025.07.037 ↗
8. Multi-objective symbiotic organisms search for optimal scooter battery swapping station allocation10.1016/j.jpowsour.2025.238255 ↗
9. Battery swapping station management with heterogeneous battery functionality degradation10.1109/TSG.2024.3392259 ↗
10. Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution10.1016/j.jpowsour.2020.228964 ↗
11. A novel fault diagnosis method for lithium-ion battery packs of electric vehicles10.1016/j.measurement.2017.11.034 ↗
12. Model-free detection and quantitative assessment of micro short circuits in lithium-ion battery packs based on incremental capacity and unsupervised clustering10.1016/j.ijoes.2024.100794 ↗
13. Adaptive internal short-circuit fault detection for lithium-ion batteries of electric vehicles10.1016/j.est.2024.110874 ↗
14. Early detection of internal short circuit faults in lithium-ion battery packs using dynamic time warping and gaussian mixture clustering10.1016/j.ijoes.2025.101107 ↗
15. An exhaustive review of battery faults and diagnostic techniques for real-world electric vehicle safety10.1016/j.est.2024.113234 ↗
16. Cell consistency evaluation method based on multiple unsupervised learning algorithms10.26599/BDMA.2023.9010003 ↗
17. Online soft short-circuit diagnosis of electric vehicle li-ion batteries based on constant voltage charging current10.1109/TTE.2022.3208066 ↗
18. How battery capacities are correctly estimated considering latent short-circuit faults10.1016/j.apenergy.2024.124190 ↗
19. Online internal short circuit detection for a large format lithium ion battery10.1016/j.apenergy.2015.10.019 ↗
20. A joint online strategy of measurement outliers diagnosis and state of charge estimation for lithium-ion batteries10.1109/TII.2022.3202949 ↗
21. Soft short-circuit fault diagnosis of the lithium-ion battery pack based on an improved ekf algorithm10.2174/2212797616666230330103334 ↗
22. Multifault diagnosis of li-ion battery pack based on hybrid system10.1109/TTE.2021.3121036 ↗
23. Multi-fault diagnosis for series-connected lithium-ion battery pack with reconstruction-based contribution based on parallel pca-kpca10.1016/j.apenergy.2022.119678 ↗
24. Detection of voltage fault in lithium-ion battery based on equivalent circuit model-informed neural network
25. A novel semi-supervised fault detection and isolation method for battery system of electric vehicles10.1016/j.apenergy.2023.121650 ↗
26. Cloud-based li-ion battery anomaly detection, localization and classification10.1109/TII.2024.3514131 ↗
27. Battery fault diagnosis and failure prognosis for electric vehicles using spatio-temporal transformer networks10.1016/j.apenergy.2023.121949 ↗
28. Battery fault diagnosis for electric vehicles based on voltage abnormality by combining the long short-term memory neural network and the equivalent circuit model10.1109/TPEL.2020.3008194 ↗
29. Fault diagnosis and detection for battery system in real-world electric vehicles based on long-term feature outlier analysis10.1109/TTE.2023.3288394 ↗
30. Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods10.1016/j.apenergy.2017.05.139 ↗
31. An early fault detection method of series battery packs based on multi-feature clustering and unsupervised scoring10.1016/j.energy.2025.135754 ↗
32. An online multifault diagnosis scheme for battery packs based on voltage envelope relationship10.1109/TTE.2022.3172663 ↗
33. Data-driven fault diagnosis of internal short circuit for series-connected battery packs using partial voltage curves10.1109/TII.2024.3353872 ↗
34. Fault diagnosis for lithium-ion batteries in electric vehicles based on signal decomposition and two-dimensional feature clustering10.1016/j.geits.2022.100009 ↗
35. Physiological time-series analysis using approximate entropy and sample entropy10.1152/ajpheart.2000.278.6.H2039 ↗
36. Permutation entropy: A natural complexity measure for time series10.1103/PhysRevLett.88.174102 ↗
37. A fault diagnosis method using decomposition denoising improved multiscale weighted permutation entropy and one-versus-one least squares twin svm10.1016/j.measurement.2025.118012 ↗
38. Multi-fault diagnosis for series-connected lithium-ion battery packs based on improved sensor topology and correlation coefficient method10.1109/TASE.2024.3471253 ↗
39. Incipient fault detection based on double kullback–leibler divergence kldattw improved by a self-attention mechanism10.1016/j.ress.2025.111247 ↗
40. Fault detection for lithium-ion batteries of electric vehicles with spatio-temporal autoencoder10.1016/j.apenergy.2025.125933 ↗
41. Online multi-fault detection and diagnosis for battery packs in electric vehicles10.1016/j.apenergy.2019.114170 ↗
42. Isolation-based anomaly detection10.1145/2133360.2133363 ↗
43. A density-based algorithm for discovering clusters in large spatial databases with noise