Therefore, extracting voltage features from the charging process has attracted wide attention. In practical electric transport applications, battery charging is essential and happens regularly compared to the random discharge process affected by the driving behaviors and road environments. Such data-driven methods focus on the relationships among the input and output features, and a key part of data-driven battery state estimation is the extraction of degradation features, which largely determines the estimation performance 12, 13, 14. 11 introduced a machine learning method for the improvement of the efficiency of membrane electrode assembly design and experiment.
10 identified battery degradation patterns from impedance spectroscopy using Gaussian process machine learning models. 9 reported a promising route using machine learning to construct models that accurately predicted graphite ||LiFePO 4 (LFP) commercial cell lives using charge-discharge voltage data. The data-driven methods do not need a deep understanding of battery electrochemical principles, but large numbers of data are required to ensure the reliability of model 8. Thus, those methods using a charge/discharge process are proposed to estimate capacity for practical applications 5, 6, in which the input variables are extracted from the measured voltage curves, and the data-driven methods using statistical and machine learning techniques have been popular in battery research recently due to their strong data processing and nonlinear fitting capabilities 6, 7. The battery charging and discharging voltage, as one of the easily obtained parameters, depend on both, thermodynamic and kinetic characteristics of the battery.
#Lithium ion battery full#
In a real-life usage scenario, the battery full charge is often achieved while the EVs are parking with grid connection, however, the battery discharge depends on the user behavior with uncertainties in environmental and operational conditions, a complete discharge curve is seldom available for on-board battery health monitoring. Typically, the battery capacity is gained by a full discharge process after it has been fully charged. The accurate battery capacity estimation is challenging but critical to the reliable usage of the lithium-ion battery, i.e., accurate capacity estimation allows an accurate driving range prediction and accurate calculation of the maximum energy storage capability in a vehicle. State of Health (SoH) has been used as an indicator of the state of the battery and is usually expressed by the ratio of the relative residual capacity with respect to the initial capacity 4. However, battery degradation is an important concern in the use of lithium-ion batteries as its performance decreases over time due to irreversible physical and chemical changes 2, 3.
#Lithium ion battery portable#
Lithium-ion batteries have become the dominant energy storage device for portable electric devices, electric vehicles (EVs), and many other applications 1.
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. A transfer learning model is then developed by adding a featured linear transformation to the base model. The best model achieves a root-mean-square error of 1.1% for the dataset used for the model building. Base models that use machine learning methods are employed to estimate the battery capacity using features derived from the relaxation voltage profiles. The other two datasets, used for validation, are obtained from batteries with LiNi 0.83Co 0.11Mn 0.07O 2-based positive electrodes and batteries with the blend of Li(NiCoMn)O 2 - Li(NiCoAl)O 2 positive electrodes. One dataset is collected for model building from batteries with LiNi 0.86Co 0.11Al 0.03O 2-based positive electrodes.
Here, we report the study of three datasets comprising 130 commercial lithium-ion cells cycled under various conditions to evaluate the capacity estimation approach. In particular, exploiting the relaxation voltage curve features could enable battery capacity estimation without additional cycling information. Accurate capacity estimation is crucial for the reliable and safe operation of lithium-ion batteries.