Open Access
Issue
Published:
25 December 2023
Cell Consistency Evaluation Method Based on Multiple Unsupervised Learning Algorithms
),
Download citation
275
Views
53
Downloads
0
Crossref
0
WoS
0
Scopus
0
CSCD
Unsupervised learning algorithms can effectively solve sample imbalance. To address battery consistency anomalies in new energy vehicles, we adopt a variety of unsupervised learning algorithms to evaluate and predict the battery consistency of three vehicles using charging fragment data from actual operating conditions. We extract battery-related features, such as the mean of maximum difference, standard deviation, and entropy of batteries and then apply principal component analysis to reduce the dimensionality and record the amount of preserved information. We then build models through a collection of unsupervised learning algorithms for the anomaly detection of cell consistency faults. We also determine whether unsupervised and supervised learning algorithms can address the battery consistency problem and document the parameter tuning process. In addition, we compare the prediction effectiveness of charging and discharging features modeled individually and in combination, determine the choice of charging and discharging features to be modeled in combination, and visualize the multidimensional data for fault detection. Experimental results show that the unsupervised learning algorithm is effective in visualizing and predicting vehicle core conformance faults, and can accurately predict faults in real time. The “distance+boxplot” algorithm shows the best performance with a prediction accuracy of 80%, a recall rate of 100%, and an F1 of 0.89. The proposed approach can be applied to monitor battery consistency faults in real time and reduce the possibility of disasters arising from consistency faults.
menu
Cell Consistency Evaluation Method Based on Multiple Unsupervised Learning Algorithms
),
Abstract
Unsupervised learning algorithms can effectively solve sample imbalance. To address battery consistency anomalies in new energy vehicles, we adopt a variety of unsupervised learning algorithms to evaluate and predict the battery consistency of three vehicles using charging fragment data from actual operating conditions. We extract battery-related features, such as the mean of maximum difference, standard deviation, and entropy of batteries and then apply principal component analysis to reduce the dimensionality and record the amount of preserved information. We then build models through a collection of unsupervised learning algorithms for the anomaly detection of cell consistency faults. We also determine whether unsupervised and supervised learning algorithms can address the battery consistency problem and document the parameter tuning process. In addition, we compare the prediction effectiveness of charging and discharging features modeled individually and in combination, determine the choice of charging and discharging features to be modeled in combination, and visualize the multidimensional data for fault detection. Experimental results show that the unsupervised learning algorithm is effective in visualizing and predicting vehicle core conformance faults, and can accurately predict faults in real time. The “distance+boxplot” algorithm shows the best performance with a prediction accuracy of 80%, a recall rate of 100%, and an F1 of 0.89. The proposed approach can be applied to monitor battery consistency faults in real time and reduce the possibility of disasters arising from consistency faults.
References(11)
Y. J. Han, H. Y. Yuan, J. Li, J. Du, Y. M. Hu, and X. J. Huang, Study on influencing factors of consistency in manufacturing process of vehicle Lithium-Ion battery based on correlation coefficient and multivariate linear regression model, Advanced. Theory. Simul., vol. 4, pp. 1–8, 2021.
F. Wang, Z. Zhao, J. Ren, Z. Zhai, S. Wang, and X. Chen, A transferable lithium-ion battery remaining useful life prediction method from cycle-consistency of degradation trend, J. Power Sources, vol. 521, p. 230975, 2022.
W. Han, K. Yu, L. Mao, Q. He, Q. Wu, and Z. Li, Evaluation of lithium-ion battery pack capacity consistency using one-dimensional magnetic field scanning, IEEE. Trans. Instrum. Meas., vol. 71, p. 3507610, 2022.
F. Wang, Z. Zhao, Z. Zhai, S. Wang, B. Ding, and X. Chen, Remaining useful life prediction of lithium-ion battery based on cycle-consistency learning, in Proc. Int. Conf. Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence, Nanjing, China, 2021, pp. 1–6.
Q. Wang and W. Qi, Study on influence of sorting parameters to lithium-ion battery pack life-cycles based on cell consistency, Int. J. Electr. Hyb. Veh., vol. 10, no. 3, pp. 223–235, 2018.
H. Wang, Z. Tao, Q. Ma, Y. Fu, H. Bai, Y. Zhu, H. Xiao, and H. Bai, Impact of initial open-circuited potential on the consistency of lithium ion battery, IOP Conf. Ser.: Earth Environ. Sci., vol. 153, no. 2, p. 022023, 2018.
Y. Lu, K. Li, X. Han, X. Feng, Z. Chu, L. Lu, P. Huang, Z. Zhang, Y. Zhang, F. Yin, et, al., A method of cell-to-cell variation evaluation for battery packs in electric vehicles with charging cloud data, eTransportation, vol. 6, pp. 2590−1168, 2020.
Y. R. Ji, J. Pang, L. Tang, and Z. Ding, Research progress in evaluation methods of consistency of Li-ion power battery, Battery, vol. 44, no. 1, pp. 53–56, 2014.
J. Q. Tian, Y. J. Wang, C. Liu, and Z. H. Chen, Consistency evaluation and cluster analysis for lithium-ion battery pack in electric vehicles, Energy, vol. 194, p. 116944, 2020.
X. Bai, J. Tan, X. Wang, L. Wang, C. Liu, L. Shi, and W. Sun, Study on distributed lithium-ion power battery grouping scheme for efficiency and consistency improvement, J. Clean. Prod., vol. 233, pp. 429–445, 2019.
Publication history
Copyright
Rights and permissions
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
FEEDBACK 
TOP