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

2026-03-09

AI Summary

This work addresses the challenge of accurate state-of-charge (SoC) estimation in silicon–carbon anode batteries, which exhibit pronounced voltage hysteresis that complicates conventional estimation approaches. Existing methods struggle to simultaneously quantify uncertainty and maintain computational efficiency. To overcome this, we propose a data-driven probabilistic framework for predicting the hysteresis factor, integrating statistical and deep learning models within a cross-condition data harmonization scheme that unifies multiple driving cycles. Our approach enables precise prediction of both the hysteresis factor and its associated uncertainty while preserving computational tractability. Notably, this is the first study to implement uncertainty-aware hysteresis modeling in silicon–carbon anode systems. We systematically evaluate the model’s generalization to unseen vehicle types under zero-shot, fine-tuning, and joint-training strategies, demonstrating robust performance and significantly improved SoC estimation accuracy—thereby advancing the practical deployment of high-energy-density batteries.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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/

Problem

• voltage hysteresis
• state-of-charge estimation
• silicon-graphite anode
• uncertainty quantification
• battery modeling

Innovation

• probabilistic hysteresis prediction
• silicon-graphite anode
• data harmonization
• uncertainty quantification
• state-of-charge estimation