Mike Kopp

Mr. Mike Kopp

University of Stuttgart, Stuttgart, Baden-Württemberg, Germany

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2021 in Batteries
Verified
Journal Article
Open access
PDF file
MSMarco Ströbel
Marco Ströbel
JPJulia Pross-Brakhage
Julia Pross-Brakhage
MKMike Kopp
Mike Kopp
Kai Peter BirkeKai Peter Birke
Kai Peter Birke
Tracking the cell temperature is critical for battery safety and cell durability. It is not feasible to equip every cell with a temperature sensor in large battery systems such as those in electric vehicles. Apart from this, temperature sensors are usually mounted on the cell surface and do not detect the core temperature, which can mean detecting an offset due to the temperature gradient. Many sensorless methods require great computational effort for solving partial differential equations or require error-prone parameterization. This paper presents a sensorless temperature estimation method for lithium ion cells using data from electrochemical impedance spectroscopy in combination with artificial neural networks (ANNs). By training an ANN with data of 28 cells and estimating the cell temperatures of eight more cells of the same cell type, the neural network (a simple feed forward ANN with only one hidden layer) was able to achieve an estimation accuracy of ΔT= 1 K (10 ∘C <T< 60 ∘C) with low computational effort. The temperature estimations were investigated for different cell types at various states of charge (SoCs) with different superimposed direct currents. Our method is easy to use and can be completely automated, since there is no significant offset in monitoring temperature. In addition, the prospect of using the above mentioned approach to estimate additional battery states such as SoC and state of health (SoH) is discussed.

15 April 2022 in Batteries
Verified
Journal Article
Open access
PDF file
MKMike Kopp
Mike Kopp
MSMarco Ströbel
Marco Ströbel
AFAlexander Fill
Alexander Fill
JPJulia Pross-Brakhage
Julia Pross-Brakhage
Kai Peter BirkeKai Peter Birke
Kai Peter Birke
The temperature in each cell of a battery system should be monitored to correctly track aging behavior and ensure safety requirements. To eliminate the need for additional hardware components, a software based prediction model is needed to track the temperature behavior. This study looks at machine learning algorithms that learn physical behavior of non-linear systems based on sample data. Here, it is shown how to improve the prediction accuracy using a new method called “artificial feature extraction” compared to classical time series approaches. We show its effectiveness on tracking the temperature behavior of a Li-ion cell with limited training data at one defined ambient temperature. A custom measuring system was created capable of tracking the cell temperature, by installing a temperature sensor into the cell wrap instead of attaching it to the cell housing. Additionally, a custom early stopping algorithm was developed to eliminate the need for further hyperparameters. This study manifests that artificially training sub models that extract features with high accuracy aids models in predicting more complex physical behavior. On average, the prediction accuracy has been improved by ΔTcell=0.01 °C for the training data and by ΔTcell=0.007 °C for the validation data compared to the base model. In the field of electrical energy storage systems, this could reduce costs, increase safety and improve knowledge about the aging progress in an individual cell to sort out for second life applications.