Article
Thermodynamics
Hanqing Yu, Lisheng Zhang, Wentao Wang, Shen Li, Siyan Chen, Shichun Yang, Junfu Li, Xinhua Liu
Summary: In order to ensure the secure and healthy usage of lithium-ion batteries, accurately estimating the state of charge (SOC) in battery management systems is necessary. The development of deep learning (DL) provides a new solution for battery SOC estimation. This paper proposes a method that integrates mechanism knowledge of the battery domain into the DL framework, resulting in improved SOC estimation performance.
Article
Energy & Fuels
Omid Rezaei, Ali Rahdan, Sohrab Sardari, Masoud Dahmardeh, Zhanle Wang
Summary: This paper proposes a novel fuzzy robust two-stage unscented Kalman filter (FRTSUKF) method for the practical state of charge (SoC) estimation of lithium-ion batteries. The proposed estimator is able to estimate the model uncertainties without requiring the statistical characteristics of the uncertainties. Using the estimated uncertainties, the SoC estimation is corrected, eliminating the destructive effect of model inaccuracy on the estimation accuracy.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Haisheng Guo, Xudong Han, Run Yang, Jinjin Shi
Summary: This paper proposes a multi-scale estimation algorithm that combines fractional order adaptive extended Kalman filter and variable forgetting factor recursive least square to solve the problem of SoC estimation in lithium-ion battery management system. Experimental results show that the proposed method achieves high accuracy and robustness.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Mehmet Korkmaz
Summary: Accurate state-of-charge (SoC) estimation is crucial for the efficient management and protection of Li-Ion batteries, especially in electrified vehicles. However, the complexity of electrochemical reactions and environmental variables make accurate SoC estimation challenging. Traditional methods suffer from limitations, while data-driven approaches have gained popularity for building models based on battery parameters. This study aims to comprehensively compare ML methods and evaluate the effectiveness of different filters for outlier removal in improving SoC estimation.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Shulin Liu, Xia Dong, Xiaodong Yu, Xiaoqing Ren, Jinfeng Zhang, Rui Zhu
Summary: This paper presents an adaptive unscented Kalman filter algorithm (AUKF) for the joint estimation of SOC and SOH of lithium-ion batteries. The proposed method is verified to be accurate and reliable through experiments.
Article
Energy & Fuels
Jishu Guo, Shulin Liu, Rui Zhu
Summary: This paper proposes the use of an unscented Kalman filter (UKF) method to improve the accuracy of battery state of charge (SOC) estimation. The method involves establishing a battery model using the least squares algorithm and estimating SOC using UKF. Experiments were conducted on LiFePO4 batteries under different operating conditions and the results were compared with those of the extended Kalman filter. The comparison showed that the UKF method provided better accuracy in battery SOC estimation, with an estimation error of less than 2%.
FRONTIERS IN ENERGY RESEARCH
(2023)
Article
Engineering, Chemical
Huixin Tian, Jianhua Chen
Summary: Accurate estimation of SOC is crucial for vehicle management systems. This paper introduces an attention-based CONV-LSTM module for SOC prediction, based on CNN and LSTM networks, which shows promising results in experiments.
Article
Engineering, Electrical & Electronic
Xingchen Zhang, Yujie Wang, Zonghai Chen
Summary: Lithium-ion batteries and their control technologies are crucial for electric and intelligent transportation. Dynamic thermal management is an important technology for intelligent battery management systems. This article proposes a distributed control-oriented electro-thermal coupling model and improved parameter identification methods based on it. A state of charge (SoC)-modified core temperature estimation method is also proposed. Experimental results show high accuracy and robustness of the proposed methods.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2023)
Article
Thermodynamics
E. Jiaqiang, Bin Zhang, Yan Zeng, Ming Wen, Kexiang Wei, Zhonghua Huang, Jingwei Chen, Hao Zhu, Yuanwang Deng
Summary: This paper investigates the essence of inconsistency in lithium-ion batteries as State-Of-Charge (SOC) inconsistency, proposing a method to describe battery inconsistency using SOC disparity and studying the equalization control strategy. Through simulations and experiments, it is shown that active equalization significantly improves cell inconsistency and enhances energy utilization in the battery pack during charging and discharging processes. The proposed SOC estimation method meets accuracy requirements, and the equalization strategies effectively minimize SOC and voltage disparities among battery cells.
Article
Automation & Control Systems
Yang Li, Zhongbao Wei, Binyu Xiong, D. Mahinda Vilathgamuwa
Summary: This article proposes a computationally efficient state estimation method for lithium-ion batteries based on a degradation-conscious high-fidelity electrochemical-thermal model. The algorithm uses an ensemble-based state estimator with the singular evolutive interpolated Kalman filter (SEIKF) to ease the computational burden caused by the nonlinear nature of the battery model. Unlike existing schemes, the proposed algorithm ensures mass conservation without additional constraints, simplifying the tuning process and improving convergence speed. The proposed scheme addresses model uncertainty and measurement errors through adaptive adjustment of the SEIKF's error covariance matrices. Comparisons with well-established nonlinear estimation techniques show that the adaptive ensemble-based Li-ion battery state estimator provides excellent performance in terms of accuracy, computational speed, and robustness.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Thermodynamics
Hangyu Cheng, Seunghun Jung, Young-Bae Kim
Summary: This study utilizes phase change material as the battery thermal management method and explores the optimal arrangement using deep reinforcement learning (DRL). Compared with traditional optimization methods, DRL optimization reduces the maximum temperature and average temperature of PCM, resulting in better results.
APPLIED THERMAL ENGINEERING
(2024)
Article
Chemistry, Physical
Jinpeng Tian, Cheng Chen, Weixiang Shen, Fengchun Sun, Rui Xiong
Summary: Accurate state of charge (SOC) is crucial for the reliable operations of lithium-ion batteries. Deep learning technique has recently emerged as a promising solution for accurate SOC estimation, especially in the era of battery big data. This article reviews the deep learning-based SOC estimation framework and the recent applications of deep learning in SOC estimation, focusing on the model structure. It also discusses advanced applications like transfer learning and the combination of deep learning with other methods. Finally, it examines the challenges and future opportunities in data collection, model development, and real-world applications in this area.
ENERGY STORAGE MATERIALS
(2023)
Article
Automation & Control Systems
Kandasamy Varatharajalu, Mathankumar Manoharan, Thamil Selvi C. Palanichamy, Sivaranjani Subramani
Summary: This manuscript proposes a hybrid method, WSO-HDLNN, for measuring the battery's dynamic electrical response as it is compressed by an external force. The proposed method aims to reduce the battery-voltage error by combining the War Strategy Optimization algorithm and Hierarchical Deep Learning Neural Network. The results show that the proposed method outperforms existing approaches in terms of computation time and error.
Article
Automation & Control Systems
Wenjie Zhang, Liye Wang, Lifang Wang, Chenglin Liao, Yuwang Zhang
Summary: This article presents a joint state-of-charge (SOC) and state-of-available-power (SOAP) estimation method based on online battery model parameter identification. The improved ABSE achieves higher accuracy than the ABSE at different battery aging states, and it can accurately estimate the SOC and SOAB-based SOAP.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Engineering, Aerospace
Min Young Yoo, Jung Heon Lee, Joo-Ho Choi, Jae Sung Huh, Woosuk Sung
Summary: This paper presents a framework for accurately estimating SOC and current sensor bias in a hybrid propulsion urban air mobility (UAM) system. Realistic test profiles reflecting actual operational scenarios for the UAM are used to model the battery and validate the state estimator. The framework ensures reliable state estimation, even during transitions between operational modes, by concurrently estimating and correcting the current sensor bias.
