Gaussian process-based online health monitoring and fault analysis of lithium-ion battery systems from field data
Name
1-s2.0-S2666386424005630-main.pdf
Description
Published version
Size
6.87 MB
Format
Adobe PDF
Checksum (MD5)
9d4829360351a622956ea16c6043fd72
Author(s)
Schaeffer, Joachim
Lenz, Eric
Gulla, Duncan
Bazant, Martin Z
Braatz, Richard D
Findeisen, Rolf
Date Issued
October 2024
Journal
Cell Reports Physical Science
Publisher
Elsevier BV
Citation
Schaeffer, Joachim, Lenz, Eric, Gulla, Duncan, Bazant, Martin Z, Braatz, Richard D et al. 2024. "Gaussian process-based online health monitoring and fault analysis of lithium-ion battery systems from field data." Cell Reports Physical Science, 5 (11).
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/j.xcrp.2024.102258
