Data-driven battery aging diagnostics and lifetime extension
Doktorsavhandling, 2024
This thesis presents a series of machine learning (ML) frameworks developed using field data from vehicles and laboratory cycling data. One proposed framework is a battery capacity estimation algorithm that integrates multiple ML models with a Kalman filter, accommodating the diverse usage profiles of electric vehicles (EVs) in real-world scenarios. To reduce warranty costs, a histogram-based usage-related ML framework is developed, combining offline global models with online cell-specific models to track and predict future aging. Additionally, a remaining useful life (RUL) prediction model improves accuracy by combining usage and time-series data is developed as well.
Beyond aging diagnostics, the thesis proposes a method to extract relationships between battery performance indicators (PIs) and various influencing factors like temperature, SoC, and aging, using a neural network-based framework. Lastly, it introduces an online method to estimate battery plating potential, enabling faster charging while minimizing lithium plating risks to extend the lifetime of the battery. Collectively, these contributions provide practical tools for diagnostics, prognostics, and control, advancing safer, more efficient, and cost-effective use of Li-ion batteries in EVs.
battery management system
machine learning
neural network
state of health
remaining useful life
Lithium-ion batteries
fast charging
Författare
Yizhou Zhang
Chalmers, Elektroteknik, System- och reglerteknik
State of health estimation for lithium-ion batteries under arbitrary usage using data-driven multi-model fusion
IEEE Transactions on Transportation Electrification,;Vol. 10(2024)p. 1494-1507
Artikel i vetenskaplig tidskrift
A machine learning-based framework for online prediction of battery ageing trajectory and lifetime using histogram data
Journal of Power Sources,;Vol. 526(2022)
Artikel i vetenskaplig tidskrift
Early prediction of battery life by learning from both time-series and histogram data
IFAC Proceedings Volumes (IFAC-PapersOnline),;Vol. 56(2023)p. 3770-3775
Paper i proceeding
Machine learning-based lifelong estimation of lithium plating potential: A path to health-aware fastest battery charging
Energy Storage Materials,;(2024)
Artikel i vetenskaplig tidskrift
Yizhou Zhang, Torsten Wik, John Bergström, Shafiq Urréhman, Changfu Zou, “Harmonizing performance indicators and unifying data for lifelong battery management"
Why Are Batteries Important?
Batteries are crucial for electric vehicles and renewable energy systems, often accounting for up to half of an EV’s cost. They are sensitive to improper operation and play a vital role in reducing carbon emissions by enabling clean energy storage and transportation.
Why Does Battery Aging Diagnostics Matter?
Batteries degrade over time in complex ways, affecting their safety, performance, and cost-efficiency. Just as people need health check-ups, batteries require diagnostics to monitor their aging process, ensuring they operate efficiently and last longer.
How Can We Use Battery Aging Information?
By understanding battery aging, we can optimize operating conditions, such as temperature and charging patterns, to extend battery life. This thesis introduces machine learning (ML) methods to estimate battery capacity, predict remaining useful life, and assess risks like lithium plating during fast charging.
What Are the Challenges?
Battery aging is influenced by various factors, such as temperature and State of Charge (SoC), making diagnostics difficult. Real-world usage is unpredictable, and collected data can be noisy or incomplete. This thesis develops data-driven tools to overcome these challenges and provide more accurate diagnostics.
Contribution of This Thesis.
This work offers practical solutions to extend battery lifespan and improve efficiency, helping make electric vehicles more reliable and affordable, this advancing efforts to reduce carbon emissions.
Datadriven förlängning av livslängden och optimering av prestanda för fordonsbatterisystem
Energimyndigheten (2023-00611), 2023-10-01 -- 2025-03-31.
Datadriven prediktion av batteriåldring
Energimyndigheten (50187-1), 2020-08-01 -- 2023-07-31.
Drivkrafter
Hållbar utveckling
Innovation och entreprenörskap
Styrkeområden
Transport
Energi
Infrastruktur
C3SE (Chalmers Centre for Computational Science and Engineering)
Ämneskategorier
Reglerteknik
ISBN
978-91-8103-120-1
Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5578
Utgivare
Chalmers