Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation

Abstract

Accurate capacity estimation is crucial for the reliable and safe operation of lithium-ion batteries. In particular, exploiting the relaxation voltage curve features could enable battery capacity estimation without additional cycling information. Here, we report the study of three datasets comprising 130 commercial lithium-ion cells cycled under various conditions to evaluate the capacity estimation approach. One dataset is collected for model building from batteries with LiNi0.86Co0.11Al0.03O2-based positive electrodes. The other two datasets, used for validation, are obtained from batteries with LiNi0.83Co0.11Mn0.07O2-based positive electrodes and batteries with the blend of Li(NiCoMn)O2 - Li(NiCoAl)O2 positive electrodes. Base models that use machine learning methods are employed to estimate the battery capacity using features derived from the relaxation voltage profiles. The best model achieves a root-mean-square error of 1.1% for the dataset used for the model building. A transfer learning model is then developed by adding a featured linear transformation to the base model. This extended model achieves a root-mean-square error of less than 1.7% on the datasets used for the model validation, indicating the successful applicability of the capacity estimation approach utilizing cell voltage relaxation.

Deep‐Learning‐Enabled Crack Detection and Analysis in Commercial Lithium‐Ion Battery Cathodes

“…There have been a few machine-learning based methods developed in the literature including the automatic capacity estimation of lithium-ion batteries. [31] To systematically predict the performance degradation behavior of battery material it requires enough dataset collected under different operational conditions. Scientifically, it is…”

Alternating Current Impedance Probing Capacity of Lithium‐Ion Battery by Gaussian Process Regression

“…where α i is Lagrange multiplier. And α Ã can be acquired by Equation ( 9), and ω can be calculated by Equation (10). b can be derived using any single support vector after the calculation of the optimal ω.…”

“…Robert et al [8b] estimated the battery capacity by using the time series values at equispaced voltages extracted from the voltage versus time curves; ≈2–3% RMSE was achieved with a 10 s galvanostatic operation. Our previous work [ 10 ] used the features extracted from the relaxation voltage curve after being fully charged for battery capacity estimation, and the best RMSE of 1.1% is obtained. Besides the charging and discharging voltage data, alternating current (AC) impedance is also served as an important input feature for battery state estimation, [ 11 ] e.g., temperature estimation, [11c] and SoH investigation [2b,12] with high potential of onboard implementations.…”

Recent Progress in Quasi/All-Solid-State Electrolytes for Lithium–Sulfur Batteries

“…A rechargeable Li battery based on the Li chemistry is considered a promising candidate for battery systems and related functions. Typically, lithium-sulfur batteries (LSBs) are selected as ideal choices for energy storage systems due to their high theoretical-specific capacity (1,672 mA h/g) and theoretical-specific energy density (2,600 W h/kg), which is five times higher than traditional lithium-ion batteries (LIBs) (Dai et al, 2021;Zhou et al, 2021;Zhu et al, 2022). Meanwhile, compared to the lithium-ion battery, elemental sulfur, the main active material in LSBs, has the advantages of being abundantly stored, low-cost, simple to prepare, and environmentally friendly (Li et al, 2019;Gong and Wang, 2020;Liu X.-Z.…”