Graphite//LFP synthetic training diagnosis dataset

Published: 06-05-2020| Version 1 | DOI: 10.17632/bs2j56pn7y.1
Matthieu Dubarry


This training dataset was calculated using the mechanistic modeling approach. See the “Benchmark Synthetic Training Data for Artificial Intelligence-based Li-ion Diagnosis and Prognosis“ publication for mode details. More details will be added when published. The diagnosis training dataset was compiled with a resolution of 0.01 for the triplets and C/25 charges. This accounts for more than 5,000 different paths. Each path was simulated with 0.85% increases for each degradation up to 85%. This accounts for 100 simulations per path. The training dataset, therefore, contains more than 500,000 voltage vs. capacity curves. 4 Variables are included: Cell info: Contains information on the setup of the mechanistic model 1 Positive electrode 2 Negative electrode 3 Loading ration 4 Offset 5 Resistance adjustment Qnorm: normalize capacity scale for all voltage curves pathinfo: index for simulated conditions for all voltage curves 1 LLI 2 LAMPE 3 LAMNE 4 Corresponding capacity loss volt: voltage data. Each column corresponds to the voltage simulated under the conditions of the corresponding line in pathinfo.