A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature
The physics-informed neural network (PINN) has drawn much attention as it can reduce training data size and eliminate the need for physics equation identification. This paper presents the implementation of a PINN with adaptive normalization in the loss function to predict lithium-ion battery cell te...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9858911/ |
| _version_ | 1817995525349179392 |
|---|---|
| author | Gyouho Cho Mengqi Wang Youngki Kim Jaerock Kwon Wencong Su |
| author_facet | Gyouho Cho Mengqi Wang Youngki Kim Jaerock Kwon Wencong Su |
| author_sort | Gyouho Cho |
| collection | DOAJ |
| description | The physics-informed neural network (PINN) has drawn much attention as it can reduce training data size and eliminate the need for physics equation identification. This paper presents the implementation of a PINN with adaptive normalization in the loss function to predict lithium-ion battery cell temperature. In particular, the PINN was trained with the actual battery test data, and a lumped capacitance lithium-ion battery thermal relationship was applied to the loss function with the addition of a pre-layer and connection layer to the neural network architecture. The PINN architecture shows the most accurate battery temperature prediction compared with the fully connected neural network (FCN) and its variants evaluated in this study. The proposed PINN architecture has a mean square prediction error of 0.05 °C with a limited number of training data and without battery thermal model identification. |
| first_indexed | 2024-04-14T02:07:13Z |
| format | Article |
| id | doaj.art-a8dbd516babd4a23a80517cfd2fde952 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T02:07:13Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a8dbd516babd4a23a80517cfd2fde9522022-12-22T02:18:38ZengIEEEIEEE Access2169-35362022-01-0110881178812610.1109/ACCESS.2022.31996529858911A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery TemperatureGyouho Cho0Mengqi Wang1https://orcid.org/0000-0003-1979-2565Youngki Kim2https://orcid.org/0000-0003-0061-7433Jaerock Kwon3https://orcid.org/0000-0002-5687-6998Wencong Su4https://orcid.org/0000-0003-1482-3078Department of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI, USADepartment of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI, USADepartment of Mechanical Engineering, University of Michigan-Dearborn, Dearborn, MI, USADepartment of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI, USADepartment of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI, USAThe physics-informed neural network (PINN) has drawn much attention as it can reduce training data size and eliminate the need for physics equation identification. This paper presents the implementation of a PINN with adaptive normalization in the loss function to predict lithium-ion battery cell temperature. In particular, the PINN was trained with the actual battery test data, and a lumped capacitance lithium-ion battery thermal relationship was applied to the loss function with the addition of a pre-layer and connection layer to the neural network architecture. The PINN architecture shows the most accurate battery temperature prediction compared with the fully connected neural network (FCN) and its variants evaluated in this study. The proposed PINN architecture has a mean square prediction error of 0.05 °C with a limited number of training data and without battery thermal model identification.https://ieeexplore.ieee.org/document/9858911/Physics-informed neural networklithium-ion batterybattery temperature |
| spellingShingle | Gyouho Cho Mengqi Wang Youngki Kim Jaerock Kwon Wencong Su A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature IEEE Access Physics-informed neural network lithium-ion battery battery temperature |
| title | A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature |
| title_full | A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature |
| title_fullStr | A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature |
| title_full_unstemmed | A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature |
| title_short | A Physics-Informed Machine Learning Approach for Estimating Lithium-Ion Battery Temperature |
| title_sort | physics informed machine learning approach for estimating lithium ion battery temperature |
| topic | Physics-informed neural network lithium-ion battery battery temperature |
| url | https://ieeexplore.ieee.org/document/9858911/ |
| work_keys_str_mv | AT gyouhocho aphysicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT mengqiwang aphysicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT youngkikim aphysicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT jaerockkwon aphysicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT wencongsu aphysicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT gyouhocho physicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT mengqiwang physicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT youngkikim physicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT jaerockkwon physicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature AT wencongsu physicsinformedmachinelearningapproachforestimatinglithiumionbatterytemperature |