Berlin 2024 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
DY: Fachverband Dynamik und Statistische Physik
DY 34: Poster: Machine Learning, Data Science, and Reservoir Computing
DY 34.16: Poster
Mittwoch, 20. März 2024, 15:00–18:00, Poster C
Bridging the Gap: From EIS to Real-World Battery Performance with Stochastic Pulse Design — •Limei Jin1,2, Franz Bereck2, Josef Granwehr2, Rüdiger-A. Eichel2, Karsten Reuter1, and Christoph Scheurer1 — 1Fritz-Haber-Institut der MPG, Berlin — 2IEK-9, Forschungszentrum Jülich
While Electrochemical Impedance Spectroscopy (EIS) offers valuable insights into a battery's state, real-world battery operation during driving scenarios involves dynamic state changes, where current and voltage signals are far from ideally sinusoidal. To bridge the gap between EIS and real-world driving cycle analysis, we introduce the concept of a stochastic pulse design compatible with the load profile. This approach starts with frequency-based impedance data as a reference and transitions into time-based noisy permuted sinusoidal signals, eventually yielding stochastic pulse signals that more accurately reflect the complexities of real-world operation. The analysis of this multifaceted data is conducted in the latent space of an autoencoder, which comprises essential features extracted from the input data. Through latent space segmentation and its correlation with battery aging, we ensure the validity of the generated pulse signals compared to traditional EIS. Detailed point-to-point evaluations in the feature space enable the identification of the best and worst pulse load profiles, which can then be utilized to facilitate battery fast-charging and lifetime optimization.
Keywords: Stochastic pulse; Latent space; Quantile–Quantile plot; Battery aging; Charging/discharging profiles