Search: onr:"swepub:oai:DiVA.org:mdh-64015" >
Deep neural network...
Deep neural network based battery impedance spectrum prediction using only impedance at characteristic frequencies
-
- Sun, Y. (author)
- Joint Laboratory for Advanced Energy Storage and Application, School of Mechanical Engineering, Beijing Institute of Technology, No. 5 South Zhongguancun Street, Haidian District, Beijing, 100081, China
-
- Xiong, R. (author)
- Joint Laboratory for Advanced Energy Storage and Application, School of Mechanical Engineering, Beijing Institute of Technology, No. 5 South Zhongguancun Street, Haidian District, Beijing, 100081, China
-
- Wang, C. (author)
- Joint Laboratory for Advanced Energy Storage and Application, School of Mechanical Engineering, Beijing Institute of Technology, No. 5 South Zhongguancun Street, Haidian District, Beijing, 100081, China
-
show more...
-
- Tian, J. (author)
- Joint Laboratory for Advanced Energy Storage and Application, School of Mechanical Engineering, Beijing Institute of Technology, No. 5 South Zhongguancun Street, Haidian District, Beijing, 100081, China
-
- Li, Hailong, 1976- (author)
- Mälardalens universitet,Framtidens energi
-
show less...
-
Joint Laboratory for Advanced Energy Storage and Application, School of Mechanical Engineering, Beijing Institute of Technology, No 5 South Zhongguancun Street, Haidian District, Beijing, 100081, China Framtidens energi (creator_code:org_t)
- Elsevier B.V. 2023
- 2023
- English.
-
In: Journal of Power Sources. - : Elsevier B.V.. - 0378-7753 .- 1873-2755. ; 580
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Electrochemical impedance spectroscopy can be used for characterizing and monitoring the state of batteries. However, the difficulty in the onboard acquisition limits its wide applications. This work proposes a new method to obtain the impedance spectrum by using convolutional neural network, which uses the impedance measured at several characteristic frequencies as input. The characteristic frequencies are determined according to the time constants corresponding to the characteristic peaks and valleys of contact polarization and solid electrolyte interphase growth processes from the distribution of relaxation time. The proposed method is validated based on the dataset which contains the impedance spectra of eight batteries over the whole life cycle. The predictions coincide with the ground truth, with a maximum root mean square error of 0.93 mΩ. The developed method can also be quickly adapted to acquire the impedance spectrum of other batteries with different chemistries and be used for predictions of various battery states based on the transfer learning approach.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Annan elektroteknik och elektronik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Other Electrical Engineering, Electronic Engineering, Information Engineering (hsv//eng)
Keyword
- Characteristic frequencies
- Deep learning
- Electrochemical impedance spectroscopy
- Lithium-ion battery
- Transfer learning
- Convolutional neural networks
- Deep neural networks
- Forecasting
- Life cycle
- Lithium-ion batteries
- Mean square error
- Solid electrolytes
- Battery impedance
- Characteristic peaks
- Characteristic-frequency
- Convolutional neural network
- Electrochemical-impedance spectroscopies
- Impedance spectrum
- Network-based
- Time-constants
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database