Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation
State of Charge (SOC) estimation is vital for battery management systems (BMS), impacting battery efficiency and lifespan. Accurate SOC estimation is challenging due to battery complexity and limited data for training Machine Learning based models. Transfer learning (TL) leverages pre-trained models...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10329349/ |
| _version_ | 1797364298518888448 |
|---|---|
| author | Panagiotis Eleftheriadis Spyridon Giazitzis Sonia Leva Emanuele Ogliari |
| author_facet | Panagiotis Eleftheriadis Spyridon Giazitzis Sonia Leva Emanuele Ogliari |
| author_sort | Panagiotis Eleftheriadis |
| collection | DOAJ |
| description | State of Charge (SOC) estimation is vital for battery management systems (BMS), impacting battery efficiency and lifespan. Accurate SOC estimation is challenging due to battery complexity and limited data for training Machine Learning based models. Transfer learning (TL) leverages pre-trained models, reducing training time and improving generalization in SOC estimation. In this paper, 8 different transfer learning techniques are examined, which were applied in four different models (LSTM, GRU, BiLSTM, and BiGRU) for SOC estimation. These transfer learning techniques have been applied to three datasets for re-training the models and results have been compared with the same models defined by Bayesian Hyperparameter Optimization. The TL4 and TL5 techniques consistently stood out as among the most efficient in both accuracy and computational time. |
| first_indexed | 2024-03-08T16:33:16Z |
| format | Article |
| id | doaj.art-7492e2b710eb445fbcf56bdf5d3d56ca |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T16:33:16Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7492e2b710eb445fbcf56bdf5d3d56ca2024-01-06T00:01:52ZengIEEEIEEE Access2169-35362024-01-0112993100410.1109/ACCESS.2023.333721510329349Transfer Learning Techniques for the Lithium-Ion Battery State of Charge EstimationPanagiotis Eleftheriadis0https://orcid.org/0000-0002-3604-2072Spyridon Giazitzis1Sonia Leva2https://orcid.org/0000-0002-7883-0034Emanuele Ogliari3https://orcid.org/0000-0002-2106-0374Department of Energy, Politecnico di Milano, Milan, ItalyDepartment of Energy, Politecnico di Milano, Milan, ItalyDepartment of Energy, Politecnico di Milano, Milan, ItalyDepartment of Energy, Politecnico di Milano, Milan, ItalyState of Charge (SOC) estimation is vital for battery management systems (BMS), impacting battery efficiency and lifespan. Accurate SOC estimation is challenging due to battery complexity and limited data for training Machine Learning based models. Transfer learning (TL) leverages pre-trained models, reducing training time and improving generalization in SOC estimation. In this paper, 8 different transfer learning techniques are examined, which were applied in four different models (LSTM, GRU, BiLSTM, and BiGRU) for SOC estimation. These transfer learning techniques have been applied to three datasets for re-training the models and results have been compared with the same models defined by Bayesian Hyperparameter Optimization. The TL4 and TL5 techniques consistently stood out as among the most efficient in both accuracy and computational time.https://ieeexplore.ieee.org/document/10329349/Transfer learninglithium-ion batterymachine learningstate of charge |
| spellingShingle | Panagiotis Eleftheriadis Spyridon Giazitzis Sonia Leva Emanuele Ogliari Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation IEEE Access Transfer learning lithium-ion battery machine learning state of charge |
| title | Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation |
| title_full | Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation |
| title_fullStr | Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation |
| title_full_unstemmed | Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation |
| title_short | Transfer Learning Techniques for the Lithium-Ion Battery State of Charge Estimation |
| title_sort | transfer learning techniques for the lithium ion battery state of charge estimation |
| topic | Transfer learning lithium-ion battery machine learning state of charge |
| url | https://ieeexplore.ieee.org/document/10329349/ |
| work_keys_str_mv | AT panagiotiseleftheriadis transferlearningtechniquesforthelithiumionbatterystateofchargeestimation AT spyridongiazitzis transferlearningtechniquesforthelithiumionbatterystateofchargeestimation AT sonialeva transferlearningtechniquesforthelithiumionbatterystateofchargeestimation AT emanueleogliari transferlearningtechniquesforthelithiumionbatterystateofchargeestimation |