Probabilistic Hysteresis Factor Prediction for Electric Vehicle Batteries with Graphite Anodes Containing Silicon

TL;DR

This paper presents a data-driven probabilistic model for predicting hysteresis factors in silicon-graphite battery anodes, improving state-of-charge estimation under diverse conditions with uncertainty quantification.

Contribution

It introduces a novel data harmonization and deep learning framework for hysteresis prediction, addressing computational efficiency and generalizability in battery modeling.

Findings

Models accurately predict hysteresis factors with quantified uncertainties.

Framework generalizes well to unseen vehicle models through various training strategies.

Proposed approach enhances SoC estimation for silicon-graphite batteries.

Abstract

Batteries with silicon-graphite-based anodes, which offer higher energy density and improved charging performance, introduce pronounced voltage hysteresis, making state-of-charge (SoC) estimation particularly challenging. Existing approaches to modeling hysteresis rely on exhaustive high-fidelity tests or focus on conventional graphite-based lithium-ion batteries, without considering uncertainty quantification or computational constraints. This work introduces a data-driven approach for probabilistic hysteresis factor prediction, with a particular emphasis on applications involving silicon-graphite anode-based batteries. A data harmonization framework is proposed to standardize heterogeneous driving cycles across varying operating conditions. Statistical learning and deep learning models are applied to assess performance in predicting the hysteresis factor with uncertainties while considering computational efficiency. Extensive experiments are conducted to evaluate the generalizability of the optimal model configuration in unseen vehicle models through retraining, zero-shot prediction, fine-tuning, and joint training. By addressing key challenges in SoC estimation, this research facilitates the adoption of advanced battery technologies. A summary page is available at: https://runyao-yu.github.io/Porsche_Hysteresis_Factor_Prediction/