# One-shot battery degradation trajectory prediction with deep learning
# Introduction
The data and code in this repository associated with the paper 'One-shot battery degradation trajectory prediction with deep learning' by W. Li, N. Sengupta, P. Dechent, et al.
The data and code in this repository associated with the paper 'One-shot battery degradation trajectory prediction with deep learning' by W. Li, N. Sengupta, P. Dechent, D. Howey, A. Annaswamy, and D. U. Sauer.
# Raw Experimental Data
The raw dataset consists of the data from initial characterization tests (multi-pulse test, capacity test with various C-rates, qOCV test, electrochemical impedance spectroscopy at different temperatures), cycling ageing tests (high-resolution data of current, voltage, capacity, energy and temperature) and regular characterization tests (multi-pulse test, capacity test with various C-rates and qOCV test).
...
...
@@ -11,6 +10,7 @@ The raw dataset consists of the data from initial characterization tests (multi-
The processed dataset extracted the most important data from the raw dataset and consists of analyzsed data of 48 cells during ageing tests, and the change of cell capaicty, resistances at different frequency domains and temperature during ageing are provided. Furthermore, the matlab codes to extract the metrics from the dataset are provided.
# Code
The capacity degradation dataset used in the paper together with the code regarding preprocessing for deep learning. For access to the modeling code, please contact Weihan Li at weihan.li@rwth-aachen.de for the academic license.
The capacity degradation dataset used in the paper together with the code regarding preprocessing for deep learning. For access to the modeling code, please contact Weihan Li at weihan.li@isea.rwth-aachen.de for the academic license.
