Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach
The increasing adoption of Battery Electric Vehicles (BEVs) is driving advancements in battery management systems (BMS) to address challenges like cost and range anxiety, both tied to battery performance. This paper investigates various state of charge (SOC) and state of health (SOH) estimation meth...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10738796/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586861711720448 |
|---|---|
| author | Saeid Jorkesh Ryan Ahmed Saeid Habibi Reza Hosseininejad Siyuan Xu |
| author_facet | Saeid Jorkesh Ryan Ahmed Saeid Habibi Reza Hosseininejad Siyuan Xu |
| author_sort | Saeid Jorkesh |
| collection | DOAJ |
| description | The increasing adoption of Battery Electric Vehicles (BEVs) is driving advancements in battery management systems (BMS) to address challenges like cost and range anxiety, both tied to battery performance. This paper investigates various state of charge (SOC) and state of health (SOH) estimation methods, presenting a novel hybrid neural network that combines Gate Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models. Our proposed method demonstrates significant improvements in SOH and SOC estimation accuracy, with minimal training data required. Key contributions include (1) a hybrid GRU-LSTM model improving SOC/SOH accuracy, (2) self-optimization capabilities, (3) effective handling of temperature variations without OCV-SOC lookup tables, and (4) its application to various lithium battery types. Experimental results show the method achieves an RMSE of 2% and MAE of 1.7% for SOC, and an RMSE of 0.65% and MAE of 0.85% for SOH across a temperature range of −10°C to 40°C. These results indicate a reliable and cost-effective approach for BEV battery management, contributing to the wider adoption of sustainable transportation. |
| format | Article |
| id | doaj-art-679a374d4d8343fa9bd3a7cb91d79d4e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-679a374d4d8343fa9bd3a7cb91d79d4e2025-01-25T00:01:52ZengIEEEIEEE Access2169-35362025-01-0113125661258010.1109/ACCESS.2024.348859610738796Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network ApproachSaeid Jorkesh0https://orcid.org/0000-0001-7820-9224Ryan Ahmed1https://orcid.org/0009-0001-5805-2132Saeid Habibi2Reza Hosseininejad3https://orcid.org/0009-0006-1014-2354Siyuan Xu4Department of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, CanadaDepartment of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, CanadaDepartment of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, CanadaDepartment of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, CanadaDepartment of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, CanadaThe increasing adoption of Battery Electric Vehicles (BEVs) is driving advancements in battery management systems (BMS) to address challenges like cost and range anxiety, both tied to battery performance. This paper investigates various state of charge (SOC) and state of health (SOH) estimation methods, presenting a novel hybrid neural network that combines Gate Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models. Our proposed method demonstrates significant improvements in SOH and SOC estimation accuracy, with minimal training data required. Key contributions include (1) a hybrid GRU-LSTM model improving SOC/SOH accuracy, (2) self-optimization capabilities, (3) effective handling of temperature variations without OCV-SOC lookup tables, and (4) its application to various lithium battery types. Experimental results show the method achieves an RMSE of 2% and MAE of 1.7% for SOC, and an RMSE of 0.65% and MAE of 0.85% for SOH across a temperature range of −10°C to 40°C. These results indicate a reliable and cost-effective approach for BEV battery management, contributing to the wider adoption of sustainable transportation.https://ieeexplore.ieee.org/document/10738796/Battery management systems (BMS)battery electric vehiclesgate recurrent unithybrid modellong short-term memorystate of charge |
| spellingShingle | Saeid Jorkesh Ryan Ahmed Saeid Habibi Reza Hosseininejad Siyuan Xu Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach IEEE Access Battery management systems (BMS) battery electric vehicles gate recurrent unit hybrid model long short-term memory state of charge |
| title | Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach |
| title_full | Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach |
| title_fullStr | Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach |
| title_full_unstemmed | Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach |
| title_short | Battery State of Charge and State of Health Estimation Using a New Hybrid Deep Neural Network Approach |
| title_sort | battery state of charge and state of health estimation using a new hybrid deep neural network approach |
| topic | Battery management systems (BMS) battery electric vehicles gate recurrent unit hybrid model long short-term memory state of charge |
| url | https://ieeexplore.ieee.org/document/10738796/ |
| work_keys_str_mv | AT saeidjorkesh batterystateofchargeandstateofhealthestimationusinganewhybriddeepneuralnetworkapproach AT ryanahmed batterystateofchargeandstateofhealthestimationusinganewhybriddeepneuralnetworkapproach AT saeidhabibi batterystateofchargeandstateofhealthestimationusinganewhybriddeepneuralnetworkapproach AT rezahosseininejad batterystateofchargeandstateofhealthestimationusinganewhybriddeepneuralnetworkapproach AT siyuanxu batterystateofchargeandstateofhealthestimationusinganewhybriddeepneuralnetworkapproach |