Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm
Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is the key to the battery health management system. However, problems of unstable model output and extensive calculation limit the prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PS...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.937035/full |
| _version_ | 1828071462486933504 |
|---|---|
| author | Jingjin Wu Xukun Cheng Heng Huang Chao Fang Ling Zhang Xiaokang Zhao Lina Zhang Jiejie Xing |
| author_facet | Jingjin Wu Xukun Cheng Heng Huang Chao Fang Ling Zhang Xiaokang Zhao Lina Zhang Jiejie Xing |
| author_sort | Jingjin Wu |
| collection | DOAJ |
| description | Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is the key to the battery health management system. However, problems of unstable model output and extensive calculation limit the prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PSO-RF) prediction method to improve the RUL prediction accuracy. First, the battery capacity extracted from the lithium-ion battery data set of the National Aeronautics and Space Administration (NASA) and the University of Maryland Center for Advanced Life Cycle Engineering (CALCE) is set as the battery life health factor. Then, a PSO-RF prediction model is established based on the optimal parameters for the number of trees and the number of random features to split by the PSO algorithm. Finally, the experiment is verified on the NASA and CALCE data sets. The experiment results indicate that the method predicts RUL with Mean Absolute Error (MAE) less than 2%, Root Mean Square Error (RMSE) less than 3%, and goodness of fit greater than 94%. This method solves the problem of parameter selection in the RF algorithm. |
| first_indexed | 2024-04-11T00:53:44Z |
| format | Article |
| id | doaj.art-ca5ff8c4b6064a3f9cdc70086e51b818 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-11T00:53:44Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-ca5ff8c4b6064a3f9cdc70086e51b8182023-01-05T06:53:14ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-01-011010.3389/fenrg.2022.937035937035Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithmJingjin Wu0Xukun Cheng1Heng Huang2Chao Fang3Ling Zhang4Xiaokang Zhao5Lina Zhang6Jiejie Xing7Mechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaMechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaMechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaMechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaMechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaHainan Curium Technology Co., Ltd, Haikou, ChinaEngineering College, China Agricultural University, Beijing, ChinaMechanical and Electrical Engineering College, Hainan University, Haikou, Hainan, ChinaAccurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is the key to the battery health management system. However, problems of unstable model output and extensive calculation limit the prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PSO-RF) prediction method to improve the RUL prediction accuracy. First, the battery capacity extracted from the lithium-ion battery data set of the National Aeronautics and Space Administration (NASA) and the University of Maryland Center for Advanced Life Cycle Engineering (CALCE) is set as the battery life health factor. Then, a PSO-RF prediction model is established based on the optimal parameters for the number of trees and the number of random features to split by the PSO algorithm. Finally, the experiment is verified on the NASA and CALCE data sets. The experiment results indicate that the method predicts RUL with Mean Absolute Error (MAE) less than 2%, Root Mean Square Error (RMSE) less than 3%, and goodness of fit greater than 94%. This method solves the problem of parameter selection in the RF algorithm.https://www.frontiersin.org/articles/10.3389/fenrg.2022.937035/fulllithium-ion batteriesRULRFPSOmachine learning |
| spellingShingle | Jingjin Wu Xukun Cheng Heng Huang Chao Fang Ling Zhang Xiaokang Zhao Lina Zhang Jiejie Xing Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm Frontiers in Energy Research lithium-ion batteries RUL RF PSO machine learning |
| title | Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm |
| title_full | Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm |
| title_fullStr | Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm |
| title_full_unstemmed | Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm |
| title_short | Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm |
| title_sort | remaining useful life prediction of lithium ion batteries based on pso rf algorithm |
| topic | lithium-ion batteries RUL RF PSO machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.937035/full |
| work_keys_str_mv | AT jingjinwu remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT xukuncheng remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT henghuang remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT chaofang remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT lingzhang remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT xiaokangzhao remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT linazhang remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm AT jiejiexing remainingusefullifepredictionoflithiumionbatteriesbasedonpsorfalgorithm |