Aging-Aware Classification and Optimal Usage of Electric Vehicle Batteries
Doktorsavhandling, 2025

To facilitate successful market adoption of second-life battery energy storage systems (BESSs) based on new and used electric vehicle (EV) batteries, we propose aging-aware classification in first-life applications and optimal usage in second-life applications of EV batteries.

Specifically, a transferable physics-informed framework is proposed for battery degradation mode estimation and phase detection, and a quantile regression forests (QRF) model is proposed for battery lifetime early prediction, which enables aging-aware classification of EV batteries. For optimal usage of EV batteries in second-life BESS applications, an economic stage cost function is proposed to account for both the grid and the battery degradation cost, and an automatic kernel search method is extended to construct the best composite kernel for Gaussian process (GP) regression models in two battery applications.The fine-tuning strategy is proven to be effective in improving online battery degradation mode estimation and phase detection performance in the target first-life application. The QRF model can provide cycle life point prediction with high accuracy, and uncertainty quantification as the width of prediction intervals. The implicit policy incorporating historical operational data and "fixed" forecasted electricity price achieves the best economic performance, and GP regression models with the best kernel can provide better prediction performance in the two battery applications.

In summary, machine learning methods are proposed in this thesis to enable aging-aware classification in first-life applications and optimal usage in second-life applications of EV batteries, which hopefully facilitates the market adoption of second-life BESSs based on new and used EV batteries.

energy management

Lithium-ion batteries

battery degradation diagnosis

interpretable physics-informed machine learning

battery lifetime prediction

Lecture Hall EF, EDIT Building, Hörsalsvägen 11, Gothenburg
Opponent: Prof. David Howey, Department of Engineering Science, Oxford University, United Kingdom

Författare

Huang Zhang

Chalmers, Elektroteknik, System- och reglerteknik

Comparative Study of Aging-Aware Control Strategies for Grid-Connected Photovoltaic Battery Systems

Proceedings of the IEEE Conference on Decision and Control,;(2024)p. 3501-3507

Paper i proceeding

Battery capacity knee-onset identification and early prediction using degradation curvature

Journal of Power Sources,;Vol. 608(2024)

Artikel i vetenskaplig tidskrift

Scenario-Aware Machine Learning Pipeline for Battery Lifetime Prediction

2024 European Control Conference, ECC 2024,;(2024)p. 212-217

Paper i proceeding

Comparative Analysis of Battery Cycle Life Early Prediction Using Machine Learning Pipeline

IFAC-PapersOnLine,;Vol. 56(2023)p. 3757-3763

Paper i proceeding

Interpretable Battery Cycle Life Range Prediction Using Early Cell Degradation Data

IEEE Transactions on Transportation Electrification,;Vol. 9(2023)p. 2669-2682

Artikel i vetenskaplig tidskrift

Huang Zhang, Xixi Liu, Faisal Altaf, and Torsten Wik, “A Practitioner’s Guide to Automatic Kernel Search for Gaussian Processes in Battery Applications”

Huang Zhang, Xixi Liu, Faisal Altaf, and Torsten Wik, “A Transferable Physics-Informed Framework for Battery Degradation Diagnosis, Knee-Onset Detection and Knee Prediction”

An increasing number of lithium-ion batteries will be retired after reaching the end of their first lives in electric vehicles (EVs). Instead of being recycled immediately, a promising solution is to repurpose these batteries for second-life applications at a good time so that the overall value of batteries could be maximized over their service lives. Nevertheless, safe and optimal usage of EV batteries in second-life applications presents challenges that must be addressed. This thesis aims to facilitate the successful market adoption of second-life battery energy storage systems (BESSs) utilizing both new and used EV batteries. To achieve this, this thesis considers two approaches, i.e., aging-aware classification in first-life applications and optimal usage in second-life applications for EV batteries.

The results of this thesis show that aging-aware classification of EV batteries can be enabled using a transfer learning-based physics-informed framework and a battery lifetime early prediction model, while optimal usage of EV batteries can be enabled using optimal control policies that consider battery degradation and Gaussian process (GP) regression models with auto-=composite kernels that predict battery capacity and residual load in grid-connected microgrids.

Batteriåldringsmedvetet tekno-ekonomiskt beslutsstöd för optimal användning av fordonsbatterier över hela deras livslängd

Energimyndigheten, 2024-07-01 -- 2025-12-31.

Klassificering och optimal hantering av 2nd life xEV-batterier

Energimyndigheten (45540-1), 2018-10-15 -- 2023-06-30.

Ämneskategorier (SSIF 2025)

Elkraftsystem och -komponenter

Artificiell intelligens

Reglerteknik

ISBN

978-91-8103-200-0

Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5658

Utgivare

Chalmers

Lecture Hall EF, EDIT Building, Hörsalsvägen 11, Gothenburg

Online

Opponent: Prof. David Howey, Department of Engineering Science, Oxford University, United Kingdom

Relaterade dataset

Synthetic Degradation Dataset of 12 LG M50 Batteries [dataset]

DOI: 10.17632/ry6g9cc5bw.2

Mer information

Senast uppdaterat

2025-04-03