State of health estimation of lithium-ion battery cell based on optical thermometry with physics-informed machine learning DOI
Jeong-woo Jang, Junhyoung Jo, Jinsu Kim

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 140, С. 109704 - 109704

Опубликована: Ноя. 29, 2024

Язык: Английский

Thermal conductivity estimation using Physics-Informed Neural Networks with limited data DOI
Junhyoung Jo, Yeonhwi Jeong, Jinsu Kim

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 137, С. 109079 - 109079

Опубликована: Авг. 11, 2024

Язык: Английский

Процитировано

5

Physics-informed learning in artificial electromagnetic materials DOI
Yang Deng, Kebin Fan, Biaobing Jin

и другие.

Applied Physics Reviews, Год журнала: 2025, Номер 12(1)

Опубликована: Март 1, 2025

The advent of artificial intelligence—deep neural networks (DNNs) in particular—has transformed traditional research methods across many disciplines. DNNs are data driven systems that use large quantities to learn patterns fundamental a process. In the realm electromagnetic materials (AEMs), common goal is discover connection between AEM's geometry and material properties predict resulting scattered fields. To achieve this goal, usually utilize computational simulations act as ground truth for training process, numerous successful results have been shown. Although demonstrated successes, they limited by their requirement lack interpretability. latter because black-box models, therefore, it unknown how or why work. A promising approach which may help mitigate aforementioned limitations physics guide development operation DNNs. Indeed, physics-informed learning (PHIL) has seen rapid last few years with some success addressing conventional We overview field PHIL discuss benefits incorporating knowledge into deep process introduce taxonomy enables us categorize various types approaches. also summarize principles critical understanding Appendix covers AEMs. specific works highlighted serve examples Finally, we provide an outlook detailing where currently what can expect future.

Язык: Английский

Процитировано

0

A least squares–support vector machine for learning solution to multi-physical transient-state field coupled problems DOI

Xiaoming Han,

Xin Zhao,

Yecheng Wu

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 138, С. 109321 - 109321

Опубликована: Сен. 20, 2024

Язык: Английский

Процитировано

2

Discretized blank holding force driven by electromagnetics: Mechanism of thermal effects and deformation DOI
Lei Li,

Yangtong Deng,

Yue Wang

и другие.

Journal of Materials Processing Technology, Год журнала: 2024, Номер 331, С. 118493 - 118493

Опубликована: Июль 6, 2024

Язык: Английский

Процитировано

1

State of health estimation of lithium-ion battery cell based on optical thermometry with physics-informed machine learning DOI
Jeong-woo Jang, Junhyoung Jo, Jinsu Kim

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 140, С. 109704 - 109704

Опубликована: Ноя. 29, 2024

Язык: Английский

Процитировано

0