Table 2
State-of-the-art AI algorithms applied in lithium ion batteries
| Application area | Descriptions | Relevant algorithms |
| Material screening | • Identifying materials with high energy density and excellent cycle life by analyzing material properties and electrochemical performance | • CNNs, SVMs, random forests, GNNs |
| Performance prediction | • Predicting battery characteristics such as capacity retention, cycle life, charging/discharging efficiency, and aging behavior | • LSTMs, RNNs, Bayesian network, DQNs, linear regression |
| Defect detection | • Detecting defects in lithium batteries during production and usage, such as internal delamination, cracks, and thermal runaway risks | • CNNs, GANs, K-means |
| Optimization design | • Enhancing battery performance by optimizing anode and cathode materials, electrolyte composition, and structural design | • GA, Bayesian network, random Forests, GNNs, PINNs |
| Data analysis & classification | • Performing pattern recognition, classification, and clustering of experimental data to support performance consistency analysis and anomaly detection | • K-NNs, K-means |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.