Predicting lithium-ion battery health and lifespan using machine learning

Han, Yunlong (韓玉龍)

Predicting lithium-ion battery health and lifespan using machine learning

Han, Yunlong (韓玉龍)

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (6.21 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Han, Yunlong (韓玉龍)
dc.date.accessioned	2025-01-21T02:15:19Z
dc.date.available	2025-01-21T02:15:19Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/183913
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	This thesis presents new advancements in the prediction of the Remaining Useful Life (RUL) of lithium-ion batteries, with a specific focus on individual battery cells RUL prediction and battery packs State of Health (SOH). The research encapsulates novel methodologies that integrate deep learning techniques with traditional mathematical modelling, aiming to enhance the precision and reliability of SOH and RUL predictions. In Chapter 3, the study introduces a new approach for individual battery cell RUL prediction. This approach is characterized by its unique DTNN model. The method's efficiency is rigorously validated against existing models, demonstrating superior accuracy in predicting the RUL of single batteries. This enhanced precision is pivotal for optimizing battery usage and extending its operational lifespan, particularly in applications where battery reliability is critical. Chapter 4 expands the scope of the research to encompass battery pack-level SOH prediction. This part of the thesis addresses the complex dynamics within a battery pack, employing an advanced amalgamation of signal processing techniques and deep learning methodologies. The research stands out for its ability to not only improve prediction accuracy but also to tackle the challenges of operational efficiency and computational agility in large-scale battery systems. The findings from this chapter are crucial for the development of more robust battery management systems, particularly in scenarios where understanding the collective behaviour of battery cells is essential. The integration of these methodologies across individual cells and battery packs represents a significant advancement in the field of battery life prediction. The dual-level analysis – single cell and pack level – provides a comprehensive understanding of battery health and life expectancy. This is particularly relevant in the context of the increasing reliance on renewable energy sources and electric vehicles, where battery performance is a key concern. The research detailed in this thesis has far-reaching implications for the design and implementation of battery management systems. By enhancing the accuracy and reliability of battery SOH and RUL predictions, the methods developed here pave the way for the optimization of battery usage in various sectors. This contributes to the broader goal of advancing renewable energy technologies and supporting the transition to more sustainable energy systems.	en_US.UTF-8
dc.format	ME (Res)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/183913/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2023 Yunlong Han (韓玉龍)
dc.rights	au.edu.uts.lib/cph
dc.title	Predicting lithium-ion battery health and lifespan using machine learning	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

This thesis presents new advancements in the prediction of the Remaining Useful Life (RUL) of lithium-ion batteries, with a specific focus on individual battery cells RUL prediction and battery packs State of Health (SOH). The research encapsulates novel methodologies that integrate deep learning techniques with traditional mathematical modelling, aiming to enhance the precision and reliability of SOH and RUL predictions. In Chapter 3, the study introduces a new approach for individual battery cell RUL prediction. This approach is characterized by its unique DTNN model. The method's efficiency is rigorously validated against existing models, demonstrating superior accuracy in predicting the RUL of single batteries. This enhanced precision is pivotal for optimizing battery usage and extending its operational lifespan, particularly in applications where battery reliability is critical. Chapter 4 expands the scope of the research to encompass battery pack-level SOH prediction. This part of the thesis addresses the complex dynamics within a battery pack, employing an advanced amalgamation of signal processing techniques and deep learning methodologies. The research stands out for its ability to not only improve prediction accuracy but also to tackle the challenges of operational efficiency and computational agility in large-scale battery systems. The findings from this chapter are crucial for the development of more robust battery management systems, particularly in scenarios where understanding the collective behaviour of battery cells is essential. The integration of these methodologies across individual cells and battery packs represents a significant advancement in the field of battery life prediction. The dual-level analysis – single cell and pack level – provides a comprehensive understanding of battery health and life expectancy. This is particularly relevant in the context of the increasing reliance on renewable energy sources and electric vehicles, where battery performance is a key concern. The research detailed in this thesis has far-reaching implications for the design and implementation of battery management systems. By enhancing the accuracy and reliability of battery SOH and RUL predictions, the methods developed here pave the way for the optimization of battery usage in various sectors. This contributes to the broader goal of advancing renewable energy technologies and supporting the transition to more sustainable energy systems.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/183913