Prediction of Li-ion battery state of health based on data-driven algorithm
Li-ion battery state of health (SOH) is a key parameter for characterizing actual battery life. SOH cannot be measured directly. In order to further improve the accuracy of Li-ion battery SOH estimation, a combined model based on health feature parameters combined with EMD-ICA-GRU is proposed to pre...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722025215 |
| _version_ | 1797952801178910720 |
|---|---|
| author | Hanlei Sun Dongfang Yang Jiaxuan Du Ping Li Kai Wang |
| author_facet | Hanlei Sun Dongfang Yang Jiaxuan Du Ping Li Kai Wang |
| author_sort | Hanlei Sun |
| collection | DOAJ |
| description | Li-ion battery state of health (SOH) is a key parameter for characterizing actual battery life. SOH cannot be measured directly. In order to further improve the accuracy of Li-ion battery SOH estimation, a combined model based on health feature parameters combined with EMD-ICA-GRU is proposed to predict the SOH of Li-ion batteries. The capacity regeneration phenomenon and data noise are decomposed by empirical mode decomposition (EMD), and then the SOH-related health indicators are deeply mined using incremental capacity analysis (ICA), and the peaks of IC curves and their corresponding voltages are extracted as the input of the model. Then, gated recurrent units (GRUs) are formed into a combined SOH estimation model by adaptive weighting factors. Finally, it is validated against the NASA lithium battery dataset. Experimental results show that the mean squared error (MSE) of the proposed combined model can reach about 0.3%, and it has stronger generalization and prediction accuracy than other algorithms driven by independent estimation data. |
| first_indexed | 2024-04-10T22:52:50Z |
| format | Article |
| id | doaj.art-a7e77225ad014b2f9a60947d34bbc9ab |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T22:52:50Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-a7e77225ad014b2f9a60947d34bbc9ab2023-01-15T04:22:10ZengElsevierEnergy Reports2352-48472022-11-018442449Prediction of Li-ion battery state of health based on data-driven algorithmHanlei Sun0Dongfang Yang1Jiaxuan Du2Ping Li3Kai Wang4School of Electrical Engineering, Weihai Innovation Research Institute, Qingdao University, Qingdao, 266000, ChinaXi’an Traffic Engineering Institute, Xi’an, 710300, ChinaNortheast Electric Power University, Ji’lin, 132012, ChinaDongying District Science and Technology Bureau, Dong’ying, 257073, ChinaSchool of Electrical Engineering, Weihai Innovation Research Institute, Qingdao University, Qingdao, 266000, China; Corresponding author.Li-ion battery state of health (SOH) is a key parameter for characterizing actual battery life. SOH cannot be measured directly. In order to further improve the accuracy of Li-ion battery SOH estimation, a combined model based on health feature parameters combined with EMD-ICA-GRU is proposed to predict the SOH of Li-ion batteries. The capacity regeneration phenomenon and data noise are decomposed by empirical mode decomposition (EMD), and then the SOH-related health indicators are deeply mined using incremental capacity analysis (ICA), and the peaks of IC curves and their corresponding voltages are extracted as the input of the model. Then, gated recurrent units (GRUs) are formed into a combined SOH estimation model by adaptive weighting factors. Finally, it is validated against the NASA lithium battery dataset. Experimental results show that the mean squared error (MSE) of the proposed combined model can reach about 0.3%, and it has stronger generalization and prediction accuracy than other algorithms driven by independent estimation data.http://www.sciencedirect.com/science/article/pii/S2352484722025215Lithium-ion batterySOHICAEMDGRU |
| spellingShingle | Hanlei Sun Dongfang Yang Jiaxuan Du Ping Li Kai Wang Prediction of Li-ion battery state of health based on data-driven algorithm Energy Reports Lithium-ion battery SOH ICA EMD GRU |
| title | Prediction of Li-ion battery state of health based on data-driven algorithm |
| title_full | Prediction of Li-ion battery state of health based on data-driven algorithm |
| title_fullStr | Prediction of Li-ion battery state of health based on data-driven algorithm |
| title_full_unstemmed | Prediction of Li-ion battery state of health based on data-driven algorithm |
| title_short | Prediction of Li-ion battery state of health based on data-driven algorithm |
| title_sort | prediction of li ion battery state of health based on data driven algorithm |
| topic | Lithium-ion battery SOH ICA EMD GRU |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722025215 |
| work_keys_str_mv | AT hanleisun predictionofliionbatterystateofhealthbasedondatadrivenalgorithm AT dongfangyang predictionofliionbatterystateofhealthbasedondatadrivenalgorithm AT jiaxuandu predictionofliionbatterystateofhealthbasedondatadrivenalgorithm AT pingli predictionofliionbatterystateofhealthbasedondatadrivenalgorithm AT kaiwang predictionofliionbatterystateofhealthbasedondatadrivenalgorithm |