Machine Learning-Based Lithium Battery State of Health Prediction Research
To address the problem of predicting the state of health (SOH) of lithium-ion batteries, this study develops three models optimized using the particle swarm optimization (PSO) algorithm, including the long short-term memory (LSTM) network, convolutional neural network (CNN), and support vector regre...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/516 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589255594999808 |
|---|---|
| author | Kun Li Xinling Chen |
| author_facet | Kun Li Xinling Chen |
| author_sort | Kun Li |
| collection | DOAJ |
| description | To address the problem of predicting the state of health (SOH) of lithium-ion batteries, this study develops three models optimized using the particle swarm optimization (PSO) algorithm, including the long short-term memory (LSTM) network, convolutional neural network (CNN), and support vector regression (SVR), for accurate SOH estimation. Key features were extracted by analyzing the temperature, voltage, and current curves of the battery, and health factors with high correlation to SOH were selected as model inputs using the Pearson correlation coefficient. The PSO algorithm was employed to optimize model parameters, resulting in the construction of three predictive models: PSO-LSTM, PSO-CNN, and PSO-SVR. The models were validated using the NASA PCoE battery aging datasets B0005, B0006, and B0007, with prediction accuracy evaluated based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R<sup>2</sup>). Results indicate that the optimized models achieved significant improvements in prediction accuracy, with RMSE and MAE reduced by over 0.5%, a minimum reduction of 38% in MAPE, and R<sup>2</sup> exceeding 0.8, demonstrating strong fitting capabilities and validating the effectiveness of the PSO strategy. Among the three models, PSO-LSTM exhibited the best predictive performance, achieving a minimum MAE of 0.67%, RMSE of 0.94%, MAPE of 45.82%, and R<sup>2</sup> as high as 0.9298 across the three datasets. These findings suggest that the PSO-LSTM model provides a robust reference for accurate SOH prediction of lithium-ion batteries and shows promising potential for practical applications. |
| format | Article |
| id | doaj-art-4c2b4a1512fa4ffb8a93873a3f881096 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-4c2b4a1512fa4ffb8a93873a3f8810962025-01-24T13:19:38ZengMDPI AGApplied Sciences2076-34172025-01-0115251610.3390/app15020516Machine Learning-Based Lithium Battery State of Health Prediction ResearchKun Li0Xinling Chen1School of Economics and Management, Tiangong University, Tianjin 300387, ChinaSchool of Economics and Management, Tiangong University, Tianjin 300387, ChinaTo address the problem of predicting the state of health (SOH) of lithium-ion batteries, this study develops three models optimized using the particle swarm optimization (PSO) algorithm, including the long short-term memory (LSTM) network, convolutional neural network (CNN), and support vector regression (SVR), for accurate SOH estimation. Key features were extracted by analyzing the temperature, voltage, and current curves of the battery, and health factors with high correlation to SOH were selected as model inputs using the Pearson correlation coefficient. The PSO algorithm was employed to optimize model parameters, resulting in the construction of three predictive models: PSO-LSTM, PSO-CNN, and PSO-SVR. The models were validated using the NASA PCoE battery aging datasets B0005, B0006, and B0007, with prediction accuracy evaluated based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R<sup>2</sup>). Results indicate that the optimized models achieved significant improvements in prediction accuracy, with RMSE and MAE reduced by over 0.5%, a minimum reduction of 38% in MAPE, and R<sup>2</sup> exceeding 0.8, demonstrating strong fitting capabilities and validating the effectiveness of the PSO strategy. Among the three models, PSO-LSTM exhibited the best predictive performance, achieving a minimum MAE of 0.67%, RMSE of 0.94%, MAPE of 45.82%, and R<sup>2</sup> as high as 0.9298 across the three datasets. These findings suggest that the PSO-LSTM model provides a robust reference for accurate SOH prediction of lithium-ion batteries and shows promising potential for practical applications.https://www.mdpi.com/2076-3417/15/2/516lithium-ion battery state of healthneural network modelparticle swarm algorithmsupport vector regression |
| spellingShingle | Kun Li Xinling Chen Machine Learning-Based Lithium Battery State of Health Prediction Research Applied Sciences lithium-ion battery state of health neural network model particle swarm algorithm support vector regression |
| title | Machine Learning-Based Lithium Battery State of Health Prediction Research |
| title_full | Machine Learning-Based Lithium Battery State of Health Prediction Research |
| title_fullStr | Machine Learning-Based Lithium Battery State of Health Prediction Research |
| title_full_unstemmed | Machine Learning-Based Lithium Battery State of Health Prediction Research |
| title_short | Machine Learning-Based Lithium Battery State of Health Prediction Research |
| title_sort | machine learning based lithium battery state of health prediction research |
| topic | lithium-ion battery state of health neural network model particle swarm algorithm support vector regression |
| url | https://www.mdpi.com/2076-3417/15/2/516 |
| work_keys_str_mv | AT kunli machinelearningbasedlithiumbatterystateofhealthpredictionresearch AT xinlingchen machinelearningbasedlithiumbatterystateofhealthpredictionresearch |