This training dataset was calculated using the mechanistic modeling approach. See “Big data training data for artificial intelligence-based Li-ion diagnosis and prognosis“ (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and "Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Diagnosis and Prognosis" (Energies, under review) for more details

The V vs. Q 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 at most 0.85% increases for each The training dataset, therefore, contains more than 700,000 unique voltage vs. capacity curves.

4 Variables are included, see read me file for details and example how to use. Cell info: Contains information on the setup of the mechanistic model Qnorm: normalize capacity scale for all voltage curves pathinfo: index for simulated conditions for all voltage curves volt: voltage data. Each column corresponds to the voltage simulated under the conditions of the corresponding line in pathinfo.

This dataset contains more than 700,000 unique voltage vs. capacity curves. It was calculated using the mechanistic modeling approach. See “Big data training data for artificial intelligence-based Li-ion diagnosis and prognosis“ (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and "Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis" (Energies, under review) for more details.

This 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 at most 0.85% increases for each degradation mode.

4 Variables are included, see read me file for details and example how to use.

These datasets were calculated using the mechanistic modeling approach. See “Big data training data for artificial intelligence-based Li-ion diagnosis and prognosis“ (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and "Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis" (Energies, under review) for more details

The V vs. Q dataset (Gr-NCA_Co33_cha_n) 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 at most 0.85% increases for each. The dataset contains more than 700,000 unique voltage vs. capacity curves. 4 Variables are included, see corresponding read me file for details and example how to use.

The duty cycle dataset is composed of close to 125,000 duty cycles with one voltage curve at most every 200 cycles (one every 10 cycles for cycles 1-200). 15 variables are included in the duty cycle dataset (Gr-NCA_Co33_cha_124652duty). See corresponding read me file for details and example how to use.

These datasets were calculated using the mechanistic modeling approach. See “Big data training data for artificial intelligence-based Li-ion diagnosis and prognosis“ (Journal of Power Sources, Volume 479, 15 December 2020, 228806) and "Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis" (Energies, under review) for more details

The V vs. Q dataset (Gr-NMC_Co25_cha_n) 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 at most 0.85% increases for each. The dataset contains more than 700,000 unique voltage vs. capacity curves. 4 Variables are included, see corresponding read me file for details and example how to use.

The duty cycle dataset is composed of more than 140,000 duty cycles with one voltage curve at most every 200 cycles (one every 10 cycles for cycles 1-200). 15 variables are included in the duty cycle dataset (Gr-NMC_Co25_cha_142216duty). See corresponding read me file for details and example how to use.