Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm
[Introduction] Accurate estimation of the Li-ion batteries' State of Health (SoH) is essential for future intelligent battery management systems. To solve the problems of poor quality of data features and difficulties in adjusting model parameters, this study proposes a method for estimating th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Energy Observer Magazine Co., Ltd.
2023-11-01
|
| Series: | 南方能源建设 |
| Subjects: | |
| Online Access: | https://www.energychina.press/en/article/doi/10.16516/j.gedi.issn2095-8676.2023.06.010 |
| _version_ | 1797627715326574592 |
|---|---|
| author | Chao WANG Qi CHEN Xinmei GU Hu JIANG Fang GUO Guangshan HUANG Shanshan ZHU |
| author_facet | Chao WANG Qi CHEN Xinmei GU Hu JIANG Fang GUO Guangshan HUANG Shanshan ZHU |
| author_sort | Chao WANG |
| collection | DOAJ |
| description | [Introduction] Accurate estimation of the Li-ion batteries' State of Health (SoH) is essential for future intelligent battery management systems. To solve the problems of poor quality of data features and difficulties in adjusting model parameters, this study proposes a method for estimating the SoH of lithium batteries based on singular value fixed-order noise reduction and the sparrow search algorithm which can optimize the gated recurrent unit (GRU) neural network.[Method] Firstly, three indicators highly correlated with SoH decay were extracted from the battery charge and discharge data. Noise reduction was applied to the features using singular value decomposition techniques to improve their correlation with SoH. Next, using the sparrow search algorithm to optimize the model structure and parameters of the GRU neural network improve the accuracy of estimation of SoH. Finally, the battery data sets from Centre for Advanced Life Cycle Engineering (CALCE) were used to verify the validity of the proposed model. [Result] The experimental results show that the model proposed in this study applies to the battery SoH estimation, with a maximum root mean square error (RMSE) of only 0.018 4. After data noise reduction and algorithm optimization, the RMSE of the GRU model is reduced by 55.41% compared to the initial model. [Conclusion] The method proposed in this paper accurately estimates SoH and can be used as a reference for practical engineering applications. |
| first_indexed | 2024-03-11T10:28:19Z |
| format | Article |
| id | doaj.art-1419523ec55f44caa32f642a850c9551 |
| institution | Directory Open Access Journal |
| issn | 2095-8676 |
| language | English |
| last_indexed | 2024-03-11T10:28:19Z |
| publishDate | 2023-11-01 |
| publisher | Energy Observer Magazine Co., Ltd. |
| record_format | Article |
| series | 南方能源建设 |
| spelling | doaj.art-1419523ec55f44caa32f642a850c95512023-11-15T04:27:32ZengEnergy Observer Magazine Co., Ltd.南方能源建设2095-86762023-11-01106899710.16516/j.gedi.issn2095-8676.2023.06.0102023-020Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search AlgorithmChao WANG0Qi CHEN1Xinmei GU2Hu JIANG3Fang GUO4Guangshan HUANG5Shanshan ZHU6Guangzhou Southern Investment Group Co., Ltd., Guangzhou 510663, Guangdong, ChinaChina Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, Guangdong, ChinaChina Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, Guangdong, ChinaGuangdong Kenuo Surveying Engineering Co., Ltd., Guangzhou 510663, Guangdong, ChinaSchool of Mechatronic Engineering and Automation, Foshan University, Foshan 528000, Guangdong, ChinaSchool of Mechatronic Engineering and Automation, Foshan University, Foshan 528000, Guangdong, ChinaSchool of Mechatronic Engineering and Automation, Foshan University, Foshan 528000, Guangdong, China[Introduction] Accurate estimation of the Li-ion batteries' State of Health (SoH) is essential for future intelligent battery management systems. To solve the problems of poor quality of data features and difficulties in adjusting model parameters, this study proposes a method for estimating the SoH of lithium batteries based on singular value fixed-order noise reduction and the sparrow search algorithm which can optimize the gated recurrent unit (GRU) neural network.[Method] Firstly, three indicators highly correlated with SoH decay were extracted from the battery charge and discharge data. Noise reduction was applied to the features using singular value decomposition techniques to improve their correlation with SoH. Next, using the sparrow search algorithm to optimize the model structure and parameters of the GRU neural network improve the accuracy of estimation of SoH. Finally, the battery data sets from Centre for Advanced Life Cycle Engineering (CALCE) were used to verify the validity of the proposed model. [Result] The experimental results show that the model proposed in this study applies to the battery SoH estimation, with a maximum root mean square error (RMSE) of only 0.018 4. After data noise reduction and algorithm optimization, the RMSE of the GRU model is reduced by 55.41% compared to the initial model. [Conclusion] The method proposed in this paper accurately estimates SoH and can be used as a reference for practical engineering applications.https://www.energychina.press/en/article/doi/10.16516/j.gedi.issn2095-8676.2023.06.010lithium batterystate of healthdata noise reductionsparrow search algorithmneural network |
| spellingShingle | Chao WANG Qi CHEN Xinmei GU Hu JIANG Fang GUO Guangshan HUANG Shanshan ZHU Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm 南方能源建设 lithium battery state of health data noise reduction sparrow search algorithm neural network |
| title | Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm |
| title_full | Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm |
| title_fullStr | Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm |
| title_full_unstemmed | Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm |
| title_short | Assessment Method for Health State of Li-Ion Batteries Based on Sparrow Search Algorithm |
| title_sort | assessment method for health state of li ion batteries based on sparrow search algorithm |
| topic | lithium battery state of health data noise reduction sparrow search algorithm neural network |
| url | https://www.energychina.press/en/article/doi/10.16516/j.gedi.issn2095-8676.2023.06.010 |
| work_keys_str_mv | AT chaowang assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT qichen assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT xinmeigu assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT hujiang assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT fangguo assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT guangshanhuang assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm AT shanshanzhu assessmentmethodforhealthstateofliionbatteriesbasedonsparrowsearchalgorithm |