This file includes two main folders with relevant data for modelling Texas Instruments BQ25505 and BQ25570 ICs.

All 6 neural network models as explained in [1] are available in both matlab and text file format. (Three models for each IC)
Matlab function include related help for the data formats.
For reproduction of NN in other programming languages, all weights from the matlab function are stored as .txt data as well.

All filtered training data as used in [1] are available in the "Training_Data" folder in the .csv format.
Voltage signals are measured in Volts while currents are in micro Ampere (uA).

Author, TU Dortmund and SFB876 are not responsible for misuse or any failures caused by use of this dataset.
Use of this data for analysis, modelling, design or other purposes is granted only with proper citation of this dataset and the related paper [1].

Part of the work on this dataset has been supported by Deutsche Forschungsgemeinschaft(DFG) within the Collaborative Research Center SFB 876 "Providing Information by Resource-Constrained Analysis", project A4.
_____________________________________
[1] Masoudinejad, M.; Magno, M.; Benini, L.; tenHompel, M.; Average Modelling of State-of-the-Art Ultra-low Power Energy Harvesting Converter IC.
in Proceeding of IEEE 2018 International Symposium on Power Electronics, Electrical Drives, Automation and Motion. Jun. 2018. Amalfi Coast, Italy.

 2016-2018 Mojtaba Masoudinejad, ALL RIGHTS RESERVED