State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States
In Li-ion battery applications, effective energy management relies heavily on accurate knowledge of the state of charge (SOC). As SOC cannot be directly measured, it must be estimated using several methods. Deep learning has emerged as one of the most widely used approaches in machine learning. Howe...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11091308/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849729263970811904 |
|---|---|
| author | Osman Ozer Hayri Arabaci |
| author_facet | Osman Ozer Hayri Arabaci |
| author_sort | Osman Ozer |
| collection | DOAJ |
| description | In Li-ion battery applications, effective energy management relies heavily on accurate knowledge of the state of charge (SOC). As SOC cannot be directly measured, it must be estimated using several methods. Deep learning has emerged as one of the most widely used approaches in machine learning. However, in cases where the input data exhibit limited variation over time and consist of low-dimensional features, deep learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) may tend toward overfitting. To address this, deep learning algorithms such as long short-term memory (LSTM) have been focused on for SOC prediction. Nevertheless, the current-voltage behavior of Li-ion cells varies significantly under different operating conditions, such as charging, discharging, and idle states. This variability negatively impacts the performance of conventional LSTM models. To overcome this limitation, this study proposes a parallel LSTM architecture composed of three distinct models, each tailored to a specific battery operating condition. Both the proposed and conventional models were evaluated using various standardized driving cycles. Mean absolute error, mean squared error, and boxplot analysis were employed for performance comparison. Across all metrics, the proposed method consistently outperformed the standard model. The best mean absolute error result was achieved with the proposed method, at 0.75% under the LA92 driving cycle. These results demonstrate the effectiveness of the proposed approach in accurately and reliably estimating SOC in dynamic battery applications. |
| format | Article |
| id | doaj-art-ae75d35b4b204713b7eb150e80b9ad5a |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ae75d35b4b204713b7eb150e80b9ad5a2025-08-20T03:09:16ZengIEEEIEEE Access2169-35362025-01-011313071913073010.1109/ACCESS.2025.359197011091308State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating StatesOsman Ozer0https://orcid.org/0000-0001-7489-1721Hayri Arabaci1https://orcid.org/0000-0002-9212-0784Department of Electrical and Electronics Engineering, Faculty of Technology, Selçuk University, Konya, TürkiyeDepartment of Electrical and Electronics Engineering, Faculty of Technology, Selçuk University, Konya, TürkiyeIn Li-ion battery applications, effective energy management relies heavily on accurate knowledge of the state of charge (SOC). As SOC cannot be directly measured, it must be estimated using several methods. Deep learning has emerged as one of the most widely used approaches in machine learning. However, in cases where the input data exhibit limited variation over time and consist of low-dimensional features, deep learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) may tend toward overfitting. To address this, deep learning algorithms such as long short-term memory (LSTM) have been focused on for SOC prediction. Nevertheless, the current-voltage behavior of Li-ion cells varies significantly under different operating conditions, such as charging, discharging, and idle states. This variability negatively impacts the performance of conventional LSTM models. To overcome this limitation, this study proposes a parallel LSTM architecture composed of three distinct models, each tailored to a specific battery operating condition. Both the proposed and conventional models were evaluated using various standardized driving cycles. Mean absolute error, mean squared error, and boxplot analysis were employed for performance comparison. Across all metrics, the proposed method consistently outperformed the standard model. The best mean absolute error result was achieved with the proposed method, at 0.75% under the LA92 driving cycle. These results demonstrate the effectiveness of the proposed approach in accurately and reliably estimating SOC in dynamic battery applications.https://ieeexplore.ieee.org/document/11091308/Li-ion batteriesstate of charge (SOC) estimationdeep learninglong-short term memorydata-driven model |
| spellingShingle | Osman Ozer Hayri Arabaci State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States IEEE Access Li-ion batteries state of charge (SOC) estimation deep learning long-short term memory data-driven model |
| title | State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States |
| title_full | State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States |
| title_fullStr | State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States |
| title_full_unstemmed | State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States |
| title_short | State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States |
| title_sort | state of charge estimation in li ion batteries using a parallel lstm based approach the impact of modeling based on operating states |
| topic | Li-ion batteries state of charge (SOC) estimation deep learning long-short term memory data-driven model |
| url | https://ieeexplore.ieee.org/document/11091308/ |
| work_keys_str_mv | AT osmanozer stateofchargeestimationinliionbatteriesusingaparallellstmbasedapproachtheimpactofmodelingbasedonoperatingstates AT hayriarabaci stateofchargeestimationinliionbatteriesusingaparallellstmbasedapproachtheimpactofmodelingbasedonoperatingstates |