ETI 06-20 Masterthesis: Developmentof a charge state estimator for lithium-ion batteries based on artificial intelligence
Institute of Electrical Engineering (ETI)
The accurate and reliable determination of the state of charge (SOC) of a battery is one of the most important topics in battery research. The state of charge can’t be measured directly and must be estimated using algorithms. A more accurate estimation prevents the battery from being oversized or enables a more efficient and safe use of the real capacity, which also has a direct influence on the economic efficiency of the battery. For this purpose, numerous estimation algorithms based on artificial intelligence are presented in the literature.
Among the most important methods are the classes of artificial neural networks (KNN) such as Feed-Forward Neural Network (FFNN), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) Network etc.
The aim of this thesis is the development of a KNN for estimating the state of charge (SOC) of lithium-ion batteries. First different KNN architectures are evaluated and the selected KNN architecture is implemented in Matlab/Simulink and/or in Python. Furthermore the test procedures are designed and cell tests are performed to determine the training and testing data. The implemented algorithm is trained and validated using the test data. Finally the algorithm is evaluated on an FPGA with real cells.
In detail the work includes the following points:
- Literature research
- Selection and implementation of the KNN architecture
- Test design and data acquisition
- Training and validation of the algorithm
- Evaluation of the algorithm on FPGA
as soon as possible
Electrical Engineering, Mechanical Engineering, Informatics
6- months according to study regulations
Contact person in line-management
Dipl.-Ing. Alexis Kalk
Phone +49 721 608-26844 (E-Mail: alexis.kalk@kit edu)
Please apply online using the button below for this vacancy number ETI 06-2020.
Ausschreibungsnummer: ETI 06-2020
If qualified, severely disabled persons will be preferred.
Personnel Support is provided by:
Phone: +49 721 608-25184,
Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany