Article
Thermodynamics
Zhikai Ma, Qian Huo, Wei Wang, Tao Zhang
Summary: This paper proposes a voltage-temperature aware thermal runaway alarming approach using advanced deep learning model, which improves the accuracy and robustness of the alarming system. Wavelet analysis is used to extract time-frequency features, deep learning with attention mechanism is adopted to map historical data to predicted data, and a voltage-temperature joint alarming method is proposed. Experiments show that the method has a combined relative error of only 0.28% for temperature and voltage prediction in a 7-minute time window and can achieve 8-13 minute ahead thermal runaway prediction in real-world scenarios.
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
Thermodynamics
Renzheng Li, Jichao Hong, Huaqin Zhang, Xinbo Chen
Summary: This paper proposes a novel SOH estimation model based on Catboost and interval capacity during the charging process, which achieves the best accuracy compared with other machine learning methods through the analysis of a year-long operation dataset of an electric taxi.
Article
Energy & Fuels
Hanlei Sun, Dongfang Yang, Jiaxuan Du, Ping Li, Kai Wang
Summary: This paper proposes a combined model based on health feature parameters combined with EMD-ICA-GRU to predict Li-ion battery SOH. By decomposing the capacity regeneration phenomenon and data noise, and mining the SOH-related health indicators, a model with higher prediction accuracy is established.
Article
Electrochemistry
Wenbin Zheng, Xinyu Zhou, Chenyu Bai, Di Zhou, Ping Fu, Matthieu Dubarry
Summary: This study proposes a method utilizing deep network adaptation to estimate battery state of health, addressing the difficulties in obtaining complete charge data under electric vehicle operating conditions and the inconsistent data distribution between source and target domains. The method demonstrates good performance in practical validation.
Article
Chemistry, Physical
Yanzhou Duan, Jinpeng Tian, Jiahuan Lu, Chenxu Wang, Weixiang Shen, Rui Xiong
Summary: In this paper, a deep learning-based method using a convolutional neural network is proposed to predict impedance spectra in lithium ion batteries over their lifespan. The results show accurate predictions of impedance spectra, validating the effectiveness of the method.
ENERGY STORAGE MATERIALS
(2021)
Article
Thermodynamics
L. Vichard, A. Ravey, P. Venet, F. Harel, S. Pelissier, D. Hissel
Summary: Batteries are complex systems that are affected by variable ambient operating conditions, and understanding their dynamic behavior and degradation laws under actual conditions is essential for durability improvement. This study proposes a method to model batteries based on experimental data from postal vehicles, which shows promising results in estimating state of health indicators linked to internal resistance and available capacity. The proposed model aims to provide accurate state of charge estimation onboard and contribute to a better understanding of battery degradation laws.
Review
Energy & Fuels
Yuefeng Liu, Yingjie He, Haodong Bian, Wei Guo, Xiaoyan Zhang
Summary: With the rapid growth in productivity, the demand for fossil fuels has increased, leading to research and development of new energy sources. Electric vehicles powered by lithium-ion batteries have become the mainstream in the automotive industry. Battery management systems are important for ensuring the safety and reliability of electric vehicle operation. Deep neural networks have been widely used in the field of battery state estimation, and this review classifies recent estimation methods based on deep learning and discusses future directions.
JOURNAL OF ENERGY STORAGE
(2022)
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
Green & Sustainable Science & Technology
Maeva Philippot, Daniele Costa, Md Sazzad Hosen, Anthony Senecat, Erwin Brouwers, Elise Nanini-Maury, Joeri Van Mierlo, Maarten Messagie
Summary: This study evaluates the second life of a NMC-LTO battery through a multidisciplinary approach and demonstrates that these batteries are suitable for reuse or repurposing. The life cycle assessment shows that the second life of the battery is beneficial for climate change under certain conditions. Reuse reduces the impact on climate change, especially in countries with a lower electricity mix. Repurposing the battery also reduces the impact on climate change and acidification.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Chemistry, Physical
Yohei Kawahara, Kei Sakabe, Ryohei Nakao, Kenichiro Tsuru, Keiichiro Okawa, Yoshinori Aoshima, Akihiko Kudo, Akihiko Emori
Summary: A new method is developed to detect the status of HEV batteries, accurately obtaining the state of charge and health of the batteries. The method also has an auto-tuning function for battery parameters, as confirmed by simulation evaluations showing less than 5% SOC error. The state of health gradually converges to the true value by repeated simulation evaluations.
JOURNAL OF POWER SOURCES
(2021)
Article
Thermodynamics
Xining Li, Lingling Ju, Guangchao Geng, Quanyuan Jiang
Summary: This paper proposes an aging feature extraction method based on an electrochemical model to account for battery degradation mechanisms. Internal health features (IHFs) such as charge transfer resistance, solid phase diffusion coefficient, and electrode volume fraction are defined, along with externally extracted health features (EHFs) from voltage and temperature curves. These features are used in data-driven SOH estimation models constructed using two machine learning algorithms, and experimental data proves the method's effectiveness in improving estimation accuracy under different scenarios and charge-discharge modes.
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.
Review
Chemistry, Physical
Shurong Lei, Song Xin, Shangxiao Liu
Summary: This paper comprehensively reviews the recent development of separate thermal management solutions for electric vehicles (EVs) and discusses in-depth the state-of-the-art integrated solutions. The benefits and drawbacks of each solution are critically commented, and the challenges faced by EV thermal management solutions and their development trends are presented.
JOURNAL OF POWER SOURCES
(2022)
Article
Computer Science, Information Systems
Dapai Shi, Jingyuan Zhao, Zhenghong Wang, Heng Zhao, Junbin Wang, Yubo Lian, Andrew F. Burke
Summary: This study proposes a specialized Transformer-based network architecture called BERTtery, which uses time-resolved battery data as input to estimate the state-of-charge (SOC) of batteries accurately. The model was trained and tested under various working conditions, demonstrating its ability to predict SOC in different scenarios of battery operation. These results showcase the predictive power of the self-attention Transformer-based model in complex battery systems.
Article
Computer Science, Information Systems
P. Radhika, T. Vigneswaran, J. Selvakumar
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2019)
Article
Computer Science, Information Systems
S. Umadevi, T. Vigneswaran
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2019)
Article
Computer Science, Information Systems
V. Sarada, T. Vigneswaran, J. Selvakumar
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2019)
Article
Telecommunications
E. Chitra, T. Vigneswaran, S. Malarvizhi
WIRELESS PERSONAL COMMUNICATIONS
(2018)
Article
Computer Science, Software Engineering
A. Maria Jossy, T. Vigneswaran, S. Malarvizhi, K. K. Nagarajan
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2019)
Article
Computer Science, Hardware & Architecture
Abraham Sudharson Ponraj, T. Vigneswaran
JOURNAL OF SUPERCOMPUTING
(2020)
Review
Computer Science, Information Systems
Sofana S. Reka, Prakash Venugopal, V Ravi, Hassan Haes Alhelou, Amer Al-Hinai, Pierluigi Siano
Summary: The automotive industry is moving towards cleaner energy by revolutionizing the industry from traditional internal combustion engines to alternative sources such as electric vehicles. The transformation requires changes and innovations in infrastructure and the study of the economic impacts of electric vehicles.
Article
Computer Science, Information Systems
Prakash Venugopal, S. Siva Shankar, C. Phillip Jebakumar, Rishab Agarwal, Hassan Haes Alhelou, S. Sofana Reka, Mohamad Esmail Hamedani Golshan
Summary: This study proposes an effective method for predicting battery aging process and accurately estimating battery health and remaining useful life. Through various factors, SOH and RUL estimation for Li-Ion 18650 cell are achieved, with experimental results showing high accuracy in predicting battery state.
Article
Computer Science, Information Systems
S. Sofana Reka, Prakash Venugopal, Hassan Haes Alhelou, Pierluigi Siano, Mohamad Esmail Hamedani Golshan
Summary: Demand response modelling plays a crucial role in smart grid by analyzing appliance scheduling and pricing strategies to determine optimal solutions for users. This research is conducted in three steps, including developing strategy patterns, learning user behavior, and creating optimal strategy plans for privacy maintenance. The study uses mathematical modelling and real-time data to validate the effectiveness of the proposed work in achieving optimal demand response strategies while ensuring user privacy.
Article
Computer Science, Information Systems
S. Nirmalraj, T. Vigneswaran
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2019)
Proceedings Paper
Computer Science, Hardware & Architecture
Rana Praful George, V. Prakash
INTELLIGENT EMBEDDED SYSTEMS, ICNETS2, VOL II
(2018)
Proceedings Paper
Computer Science, Hardware & Architecture
S. Sriram, V. Prakash
INTELLIGENT EMBEDDED SYSTEMS, ICNETS2, VOL II
(2018)
Proceedings Paper
Engineering, Electrical & Electronic
Geeta Tahalyani, Raghvendra Sahai Saxena, T. Vigneswaran
NANOELECTRONIC MATERIALS AND DEVICES, VOL III
(2018)