Siyuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Siyuan Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yuan Chen
Anhui University
2 shared publications Heng Li
1 shared publication- Xiaopeng Tang
Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR 999077, China
1 shared publication - Yanzhong Liu
School of Artificial Intelligence, Anhui University, Hefei, China
1 shared publication - Yigang He
The State Key Laboratory of Power Grid Environmental Protection, School of Electrical Engineering and Automation, Wuhan University, Wuhan, China
1 shared publication - Yujing Cai
School of Artificial Intelligence, Anhui University, Hefei, China
1 shared publication
Latest Publications
- Open Access
- 14 November 2025
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 5 (3)
Real-world vehicle charging duration prediction based on transfer learning with SENet-CNN-Transformer Model
- 14 November 2025
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 5 (3)
Open AccessReal-world vehicle charging duration prediction based on transfer learning with SENet-CNN-Transformer Model
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
SOC Estimation of Lithium-Ion Battery Pack Based on Discharge Stage Division and Fusion Modeling
To meet practical usage requirements, lithium-ion batteries usually need to form a battery pack. However, due to production deviations and different usage environments, there are inconsistencies between batteries within the battery pack. This makes it challenging to estimate the state of charge (SOC) of the battery pack accurately. This article proposes a battery pack SOC estimation approach based on discharge stage division and fusion modeling. According to the battery discharge characteristics and SOC inconsistency, three stages are divided in the battery pack discharge process. In the first stage, the second-order RC model and Extended Kalman Filter (EKF) algorithm are employed for SOC estimation as the consistency between batteries is good. In the second stage, the representative battery and Long Short-Term Memory (LSTM) recurrent neural network will be used to consider the impact of battery inconsistency on battery SOC estimation. An ampere-hour integration with constraint factor for smoothing is applied to enhance the estimation accuracy of the LSTM network. In the third stage, EKF is utilized to estimate the SOC of all batteries as the inconsistency between batteries increases significantly and reaches a maximum at the end of discharge. Finally, experiments and actual vehicle tests under the Worldwide Harmonized Light Vehicles Test Cycle (WLTC) working condition are conducted to verify the effectiveness of proposed methods on the ternary lithium battery pack at 0°C, 25°C, and 45°C. Compared with other algorithms, the proposed method has good estimation performance, with a maximum RMSE of only 0.8%. The maximum prediction error under actual vehicle operating conditions is less than 1.2%.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
SOC Estimation of Lithium-Ion Battery Pack Based on Discharge Stage Division and Fusion Modeling
To meet practical usage requirements, lithium-ion batteries usually need to form a battery pack. However, due to production deviations and different usage environments, there are inconsistencies between batteries within the battery pack. This makes it challenging to estimate the state of charge (SOC) of the battery pack accurately. This article proposes a battery pack SOC estimation approach based on discharge stage division and fusion modeling. According to the battery discharge characteristics and SOC inconsistency, three stages are divided in the battery pack discharge process. In the first stage, the second-order RC model and Extended Kalman Filter (EKF) algorithm are employed for SOC estimation as the consistency between batteries is good. In the second stage, the representative battery and Long Short-Term Memory (LSTM) recurrent neural network will be used to consider the impact of battery inconsistency on battery SOC estimation. An ampere-hour integration with constraint factor for smoothing is applied to enhance the estimation accuracy of the LSTM network. In the third stage, EKF is utilized to estimate the SOC of all batteries as the inconsistency between batteries increases significantly and reaches a maximum at the end of discharge. Finally, experiments and actual vehicle tests under the Worldwide Harmonized Light Vehicles Test Cycle (WLTC) working condition are conducted to verify the effectiveness of proposed methods on the ternary lithium battery pack at 0°C, 25°C, and 45°C. Compared with other algorithms, the proposed method has good estimation performance, with a maximum RMSE of only 0.8%. The maximum prediction error under actual vehicle operating conditions is less than 1.2%.