Article
Thermodynamics
Junxiong Chen, Xiong Feng, Lin Jiang, Qiao Zhu
Summary: A novel method combining a denoising autoencoder neural network with a gated recurrent unit recurrent neural network is proposed to reduce the impact of measurement data noise on state of charge estimation. Experimental results demonstrate that the proposed method has better accuracy and robustness in SOC estimation.
Article
Chemistry, Physical
Zheng Chen, Hongqian Zhao, Yuanjian Zhang, Shiquan Shen, Jiangwei Shen, Yonggang Liu
Summary: Accurate estimation of lithium-ion battery health is crucial for the safety and reliability of electric vehicles. This study proposes a method based on temperature prediction and neural networks to accurately estimate battery health by extracting multi-dimensional features and utilizing a gated recurrent unit neural network for prediction, achieving an error rate within 2.28%.
JOURNAL OF POWER SOURCES
(2022)
Article
Computer Science, Information Systems
Zhaowei Zhang, Zhekang Dong, Huipin Lin, Zhiwei He, Minghao Wang, Yufei He, Xiang Gao, Mingyu Gao
Summary: The proposed NAG-based Bi-GRU method leverages deep learning to estimate SOC in lithium-ion batteries, addressing issues with traditional gradient descent algorithms by optimizing the gradient updates and capturing temporal information in both forward and backward directions. Experimental results demonstrate improved precision in SOC estimation across various ambient temperatures compared to previous methods.
Article
Chemistry, Physical
Jinbo Lu, Yafeng He, Huishi Liang, Miangang Li, Zinan Shi, Kui Zhou, Zhidan Li, Xiaoxu Gong, Guoqiang Yuan
Summary: In this study, a combined SOC estimation method is proposed using a gated recurrent unit neural network and an adaptive Savitzky-Golay filter. Experimental results show that the proposed method achieves accurate and stable SOC estimation with higher accuracy and better fluctuation suppression compared to other methods.
Article
Energy & Fuels
Junxiong Chen, Yu Zhang, Wenjiang Li, Weisong Cheng, Qiao Zhu
Summary: This paper proposes a combined SOC estimation method, GRU-AKF, which uses GRU-RNN and AKF to accurately and stably estimate battery SOC. Experimental results show that the proposed method outperforms other methods in terms of SOC estimation performance and computation efficiency, particularly in terms of initial SOC convergence ability.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Chemistry, Multidisciplinary
Jianlong Chen, Chenlei Lu, Cong Chen, Hangyu Cheng, Dongji Xuan
Summary: This paper proposes a gated recurrent unit network based on genetic algorithm for state-of-charge estimation of lithium-ion batteries. By optimizing the key parameters, the performance of the network is improved. Testing under various conditions establishes training and testing datasets, and the proposed method is validated to achieve high accuracy and robustness.
APPLIED SCIENCES-BASEL
(2022)
Article
Thermodynamics
Chenyu Jia, Yukai Tian, Yuanhao Shi, Jianfang Jia, Jie Wen, Jianchao Zeng
Summary: Lithium-ion batteries are widely used and play a crucial role in various aspects of our lives. Accurate prediction of state of health (SOH) is important for the safe utilization, management, and maintenance of these batteries. A hybrid prediction model combining bidirectional gated recurrent unit (BiGRU) and Transformer with multi-head attention mechanism (AM) is proposed to effectively address the challenge of long time series prediction. The study shows that the proposed BiGRU-Transformer model has higher accuracy, better robustness, and generalization capability.
Article
Chemistry, Medicinal
Edison Mucllari, Vasily Zadorozhnyy, Qiang Ye, Duc Duy Nguyen
Summary: Advances in deep neural networks have made powerful machine learning methods available in various fields. This research proposes using new NC-GRU AutoEncoder to create neural molecular fingerprints, improving the performance of various molecular-related tasks.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Chemistry, Analytical
Yu-Chun Wang, Nei-Chun Shao, Guan-Wen Chen, Wei-Shen Hsu, Shun-Chi Wu
Summary: This study applies deep-learning techniques, specifically convolutional residual networks, to estimate the state-of-charge (SOC) of lithium-ion batteries. By stacking values of multiple measurable variables as inputs, process information for voltage or current generation can be effectively extracted, allowing accurate SOC regression.
Article
Energy & Fuels
Kuo Yang, Yanyu Wang, Yugui Tang, Shujing Zhang, Zhen Zhang
Summary: This paper proposes a deep learning model to estimate the state of charge (SOC) of lithium-ion batteries. The model combines the advantages of temporal convolutional network, gated recurrent unit network, and attention mechanism, and exhibits high accuracy and robustness in experiments under different driving conditions.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Engineering, Electrical & Electronic
Changjian Lin, Hongjian Wang, Mingyu Fu, Jianya Yuan, Jason Gu
Summary: Target state estimation is crucial for UUVs to accomplish various tasks, and underwater measurement faces challenges due to the uncertainty of sonar detection. The proposed GRU-based PF method utilizes deep neural networks to improve accuracy and stability in UUV state estimation, overcoming issues related to motion modeling errors and system nonlinearity. Simulation results demonstrate the superior performance of the GRU-based PF compared to traditional methods in handling Gaussian noise and nonlinear transformations.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Energy & Fuels
Jinpeng Tian, Rui Xiong, Weixiang Shen, Jiahuan Lu
Summary: A method based on deep neural network is proposed for fast and accurate estimation of SOC for LiFePO4 batteries, with an error of less than 2.03% over the entire battery SOC range. By integrating the DNN with a Kalman filter, the robustness of SOC estimation against random noises and error spikes can be improved.
Article
Energy & Fuels
Elias Dias Rossi Lopes, Marlon Marques Soudre, Carlos Humberto Llanos, Helon Vicente Hultmann
Summary: An important component of electric vehicles is the Battery Management System (BMS), which is responsible for monitoring the state of charge (SoC) of the battery, a crucial factor in the vehicle's autonomy. This paper proposes the use of receding-horizon strategies, specifically Moving-Horizon State Estimation (MHSE) and Neural Network Moving-Horizon Estimation (NNMHE), for accurate SoC estimation. MHSE utilizes a constrained optimization problem with a larger observation window, while NNMHE employs a neural network to emulate the optimization solver, resulting in faster and approximate results. The effectiveness of this approach is validated with experimental data, achieving a coefficient of determination of almost 99% and a processing time reduction of about 20 times, making it suitable for embedded systems with limited computational resources.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Engineering, Biomedical
Kofi Odame, Maria Nyamukuru, Mohsen Shahghasemi, Shengjie Bi, David Kotz
Summary: In this study, a novel gated recurrent neural network was developed to detect chewing events. The network was implemented as a custom analog integrated circuit and trained on data collected from a contact microphone attached to volunteers' mastoid bones. The analog neural network achieved high accuracy in identifying chewing events at a relatively low power consumption, demonstrating its potential for detecting eating episodes.
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS
(2022)
Article
Energy & Fuels
Zhimin Xi, Rui Wang, Yuhong Fu, Chris Mi
Summary: This paper proposes a time-delayed recurrent neural network for lithium ion battery modeling and SOC estimation, and analyzes its performance. It is found that overexcited neurons may cause poor performance of the neural network.
