Simultaneous Prediction of Three Key Li-Ion Battery Indicators through Multi-Task Learning
Multi-task models for state of health, DC resistance increase and maximum temperature, with battery diagnostic features and training code.
Machine-learning tools
Budget-constrained augmentation of universal interatomic potentials for reliable multicomponent molecular dynamics
An example workflow for comparing structure-sampling strategies and training interatomic potentials with a limited DFT budget. Includes a reduced example dataset.
Code (2)
Data (1)
Fast and direct diagnosis of states of health for the spent batteries
Direct state-of-health prediction with diagnostic measurements, extracted features and model training notebooks.
Data (16)
- SoC data.csv ↗
- SoC data_expandability.csv ↗
- SoH.csv ↗
- SoH_expandability.csv ↗
- SoH_features.xlsx ↗
- SoH_features_expandability.xlsx ↗
- SoH_ir_drop.csv ↗
- SoH_ir_drop_expandability.csv ↗
- SoH_resistance.csv ↗
- SoH_resistance_expandability.csv ↗
- raw_data_SoH_protocol_1.zip ↗
- raw_data_SoH_protocol_2.zip ↗
- raw_data_SoH_protocol_3.zip ↗
- raw_data_SoH_protocol_4.zip ↗
- raw_data_SoH_protocol_5.zip ↗
- raw_data_SoH_protocol_expandability.zip ↗
Laboratory automation
ALBATROSS: a robotised system for high-throughput electrolyte screening via automated electrolyte formulation, coin-cell fabrication, and electrochemical evaluation
Control software, a graphical interface and experimental data for automated electrolyte screening and coin-cell testing.