Physics and machine learning based approaches to model energy storage systems

Placeholder Show Content


Energy storage systems ensure the effective and reliable management of power supply and demand. Despite the widespread adoption, energy storage systems face substantial challenges (e.g., safety concerns, limited capacity, environmental impact), stemming from their relatively brief history in academic research and industrial applications. Motivated by these challenges, this thesis explores and develops physics and machine learning based approaches to model energy storage systems, focusing on lithium ion batteries and fuel cells. We first scrutinize the impact of mechanical and thermal factors on lithium plating in lithium ion batteries, employing both 1D and 3D physics-based models. We find that mechanical deformation can accelerate the onset of lithium plating, with folds and boundaries of jellyrolls being particularly susceptible due to distinctive mechanical conditions. Next, motivated by the crucial role of mechanical deformation in lithium plating, we develop SenseNet, a physics-informed deep learning model, for shape sensing applications. SenseNet is crafted to monitor the mechanical deformation of arbitrary structures without relying on prior knowledge of loading conditions, but utilizing a discrete network of strain sensors. Finally, given the complex nature of multiphysics problems and the notable efficiency and accuracy of machine learning methods, we explore and compare diverse data-driven approaches for fuel cell modeling.


Type of resource text
Form electronic resource; remote; computer; online resource
Extent 1 online resource.
Place California
Place [Stanford, California]
Publisher [Stanford University]
Copyright date 2023; ©2023
Publication date 2023; 2023
Issuance monographic
Language English


Author Qiu, Yitao
Degree supervisor Linder, Christian, (Engineering professor)
Thesis advisor Linder, Christian, (Engineering professor)
Thesis advisor Borja, Ronaldo I. (Ronaldo Israel)
Thesis advisor Sun, Waiching
Degree committee member Borja, Ronaldo I. (Ronaldo Israel)
Degree committee member Sun, Waiching
Associated with Stanford University, School of Engineering
Associated with Stanford University, Civil & Environmental Engineering Department


Genre Theses
Genre Text

Bibliographic information

Statement of responsibility Yitao Qiu.
Note Submitted to the Civil & Environmental Engineering Department.
Thesis Thesis Ph.D. Stanford University 2023.

Access conditions

© 2023 by Yitao Qiu
This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).

Also listed in

Loading usage metrics...