State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory
State of charge (SOC) plays a vital role in the safe, efficient, and stable operation of lithium-ion batteries. Since the difference between the surface temperature and core temperature of batteries under severe conditions can reach 5–10 °C, using the surface temperature as input feature of SOC est...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Green Energy and Intelligent Transportation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773153724000781 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595278448820224 |
|---|---|
| author | Chaoran Li Sichen Zhu Liuli Zhang Xinjian Liu Menghan Li Haiqin Zhou Qiang Zhang Zhonghao Rao |
| author_facet | Chaoran Li Sichen Zhu Liuli Zhang Xinjian Liu Menghan Li Haiqin Zhou Qiang Zhang Zhonghao Rao |
| author_sort | Chaoran Li |
| collection | DOAJ |
| description | State of charge (SOC) plays a vital role in the safe, efficient, and stable operation of lithium-ion batteries. Since the difference between the surface temperature and core temperature of batteries under severe conditions can reach 5–10 °C, using the surface temperature as input feature of SOC estimation is unreasonable. Due to the high requirement for storage space, SOC estimation methods based on deep learning methods are limited to implement in embedded devices. In this paper, to achieve reasonable and high accuracy SOC estimation and provide support for battery thermal management, SOC estimation based on state of temperature (SOT) is implemented. And weight clustered-convolutional neural network-long short-term memory (WC-CNN-LSTM) is proposed to achieve high accuracy SOT and SOC estimation with small model sizes. A self-established dataset is used to verify the effectiveness of the proposed method and model. The WC-CNN-LSTM model with the number of clusters of 400 could achieve comparative accuracy with the baseline model with a 52.98% smaller model size and 25.08% more time consumption for model training on SOT estimation. And it could also achieve consistent and even better accuracy on SOC estimation with the baseline model with a small model size. |
| format | Article |
| id | doaj-art-b7fc62c9f84d496eacb0d738408b18c5 |
| institution | Kabale University |
| issn | 2773-1537 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Green Energy and Intelligent Transportation |
| spelling | doaj-art-b7fc62c9f84d496eacb0d738408b18c52025-01-19T06:27:02ZengElsevierGreen Energy and Intelligent Transportation2773-15372025-02-0141100226State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memoryChaoran Li0Sichen Zhu1Liuli Zhang2Xinjian Liu3Menghan Li4Haiqin Zhou5Qiang Zhang6Zhonghao Rao7Hebei Engineering Research Center of Advanced Energy Storage Technology and Equipment, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Hebei Key Laboratory of Thermal Science and Energy Clean Utilization, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, ChinaHebei Engineering Research Center of Advanced Energy Storage Technology and Equipment, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Hebei Key Laboratory of Thermal Science and Energy Clean Utilization, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, ChinaPinggao Group Energy Storage Technology Co., Ltd., Room 1-4251, Block E, No. 6 Huafeng Road, Huaming High-tech Industrial Zone, Dongli District, Tianjin 300308, ChinaHebei Engineering Research Center of Advanced Energy Storage Technology and Equipment, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Hebei Key Laboratory of Thermal Science and Energy Clean Utilization, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, ChinaHebei Engineering Research Center of Advanced Energy Storage Technology and Equipment, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Hebei Key Laboratory of Thermal Science and Energy Clean Utilization, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, ChinaChemical and Environmental Engineering, University of Park, Nottingham, NG7 2RD, UKSchool of Energy and Power Engineering, Shandong University, No. 17923 Jingshi Road, Lixia District, Jinan 250061, China; Corresponding author.Hebei Engineering Research Center of Advanced Energy Storage Technology and Equipment, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Hebei Key Laboratory of Thermal Science and Energy Clean Utilization, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China; Corresponding author.State of charge (SOC) plays a vital role in the safe, efficient, and stable operation of lithium-ion batteries. Since the difference between the surface temperature and core temperature of batteries under severe conditions can reach 5–10 °C, using the surface temperature as input feature of SOC estimation is unreasonable. Due to the high requirement for storage space, SOC estimation methods based on deep learning methods are limited to implement in embedded devices. In this paper, to achieve reasonable and high accuracy SOC estimation and provide support for battery thermal management, SOC estimation based on state of temperature (SOT) is implemented. And weight clustered-convolutional neural network-long short-term memory (WC-CNN-LSTM) is proposed to achieve high accuracy SOT and SOC estimation with small model sizes. A self-established dataset is used to verify the effectiveness of the proposed method and model. The WC-CNN-LSTM model with the number of clusters of 400 could achieve comparative accuracy with the baseline model with a 52.98% smaller model size and 25.08% more time consumption for model training on SOT estimation. And it could also achieve consistent and even better accuracy on SOC estimation with the baseline model with a small model size.http://www.sciencedirect.com/science/article/pii/S2773153724000781State of chargeState of temperatureLithium-ion batteryDeep learning methodLong short-term memoryWeight cluster |
| spellingShingle | Chaoran Li Sichen Zhu Liuli Zhang Xinjian Liu Menghan Li Haiqin Zhou Qiang Zhang Zhonghao Rao State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory Green Energy and Intelligent Transportation State of charge State of temperature Lithium-ion battery Deep learning method Long short-term memory Weight cluster |
| title | State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory |
| title_full | State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory |
| title_fullStr | State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory |
| title_full_unstemmed | State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory |
| title_short | State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory |
| title_sort | state of charge estimation of lithium ion battery based on state of temperature estimation using weight clustered convolutional neural network long short term memory |
| topic | State of charge State of temperature Lithium-ion battery Deep learning method Long short-term memory Weight cluster |
| url | http://www.sciencedirect.com/science/article/pii/S2773153724000781 |
| work_keys_str_mv | AT chaoranli stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT sichenzhu stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT liulizhang stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT xinjianliu stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT menghanli stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT haiqinzhou stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT qiangzhang stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory AT zhonghaorao stateofchargeestimationoflithiumionbatterybasedonstateoftemperatureestimationusingweightclusteredconvolutionalneuralnetworklongshorttermmemory |