Data-Driven Prediction of Li-Ion Battery Degradation Using Predicted Features

被引:2
|
作者
Xing, Wei W. [1 ]
Shah, Akeel A. [2 ]
Shah, Nadir [2 ]
Wu, Yinpeng [1 ]
Xu, Qian [3 ]
Rodchanarowan, Aphichart [4 ]
Leung, Puiki [2 ]
Zhu, Xun [2 ]
Liao, Qiang [2 ]
机构
[1] Beijing Univ Aeronaut & Astronaut, Sch Integrated Circuit Sci & Engn, Beijing 100191, Peoples R China
[2] Chongqing Univ, Key Lab Low Grade Energy Utilizat Technol & Syst, Minist Educ, Chongqing 400044, Peoples R China
[3] Jiangsu Univ, Inst Energy Res, Zhenjiang 212013, Peoples R China
[4] Kasetsart Univ, Fac Engn, Dept Mat Engn, 50 Ngamwongwan Rd, Bangkok 10900, Thailand
基金
中国国家自然科学基金;
关键词
Li-ion battery degradation; feature engineering; Gaussian process mode; voltage and temperature curves; multi-step lookahead; end-of-life; REMAINING USEFUL LIFE; GAUSSIAN PROCESS REGRESSION; STATE-OF-HEALTH; PROGNOSTICS;
D O I
10.3390/pr11030678
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
For their emergent application in electric vehicles, the development of fast and accurate algorithms to monitor the health status of batteries and aid decision-making in relation to maintenance and replacement is now of paramount importance. Data-driven approaches are preferred due to the difficulties associated with defining valid models for system and parameter identification. In recent years, the use of features to enhance data-driven methods has become commonplace. Unless the data sets are from multiple batteries, however, such approaches cannot be used to predict more than one cycle ahead because the features are unavailable for future cycles, in the absence of different embedding strategies. In this paper, we propose a novel approach in which features are predicted for future cycles, enabling predictions of the state of health for an arbitrary number of cycles ahead, and, therefore, predictions for the end-of-life. This is achieved by using a data-driven approach to predict voltage and temperature curves for future cycles, from which important signatures of degradation can be extracted and even used directly for degradation predictions. The use of features is shown to enhance the state-of-health predictions. The approach we develop is capable of accurate predictions using a data set specific to the battery under consideration. This avoids the need for large multi-battery data sets, which are hampered by natural variations in the performance and degradation of batteries even from the same batch, compromising the prediction accuracy of approaches based on such data.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] Data-Driven Battery Aging Mechanism Analysis and Degradation Pathway Prediction
    Xu, Ruilong
    Wang, Yujie
    Chen, Zonghai
    BATTERIES-BASEL, 2023, 9 (02):
  • [32] Data-driven prediction of battery cycle life before capacity degradation
    Severson, Kristen A.
    Attia, Peter M.
    Jin, Norman
    Perkins, Nicholas
    Jiang, Benben
    Yang, Zi
    Chen, Michael H.
    Aykol, Muratahan
    Herring, Patrick K.
    Fraggedakis, Dimitrios
    Bazan, Martin Z.
    Harris, Stephen J.
    Chueh, William C.
    Braatz, Richard D.
    NATURE ENERGY, 2019, 4 (05) : 383 - 391
  • [33] Data-driven prediction of battery cycle life before capacity degradation
    Kristen A. Severson
    Peter M. Attia
    Norman Jin
    Nicholas Perkins
    Benben Jiang
    Zi Yang
    Michael H. Chen
    Muratahan Aykol
    Patrick K. Herring
    Dimitrios Fraggedakis
    Martin Z. Bazant
    Stephen J. Harris
    William C. Chueh
    Richard D. Braatz
    Nature Energy, 2019, 4 : 383 - 391
  • [34] Data-driven autoencoder neural network for onboard BMS Lithium-ion battery degradation prediction
    Sudarshan, Meghana
    Serov, Alexey
    Jones, Casey
    Ayalasomayajula, Surya Mitra
    Garcia, R. Edwin
    Tomar, Vikas
    JOURNAL OF ENERGY STORAGE, 2024, 82
  • [35] Supervised Learning of Synthetic Big Data for Li-Ion Battery Degradation Diagnosis
    Mayilvahanan, Karthik S.
    Takeuchi, Kenneth J.
    Takeuchi, Esther S.
    Marschilok, Amy C.
    West, Alan C.
    BATTERIES & SUPERCAPS, 2022, 5 (01)
  • [36] Data-driven autoencoder neural network for onboard BMS Lithium-ion battery degradation prediction
    Sudarshan, Meghana
    Serov, Alexey
    Jones, Casey
    Ayalasomayajula, Surya Mitra
    García, R. Edwin
    Tomar, Vikas
    Journal of Energy Storage, 2024, 82
  • [37] Data-Driven Safety Risk Prediction of Lithium-Ion Battery
    Jia, Yikai
    Li, Jiani
    Yuan, Chunhao
    Gao, Xiang
    Yao, Weiran
    Lee, Minwoo
    Xu, Jun
    ADVANCED ENERGY MATERIALS, 2021, 11 (18)
  • [38] Incremental Capacity Analysis for Prediction of Li-Ion Battery Degradation Mechanisms: Simulation Study
    Kemeny, M.
    Ondrejka, P.
    Mikolasek, M.
    2020 13TH INTERNATIONAL CONFERENCE ON ADVANCED SEMICONDUCTOR DEVICES AND MICROSYSTEMS (ASDAM 2020), 2020, : 19 - 22
  • [39] Recursive multilayer perceptron-based data-driven identification for a parameterized polarization model of rechargeable Li-ion battery
    Abbas, Mazhar
    Cho, Inho
    Kim, Jonghoon
    APPLIED SOFT COMPUTING, 2021, 101
  • [40] Analysis of Li-ion battery degradation using self-organizing maps
    Pastor-Flores, Pablo
    Bernal-Ruiz, Carlos
    Sanz-Gorrachategui, Ivan
    Bono-Nuez, Antonio
    Martin-del-Brio, Bonifacio
    Sergio Artal-Sevil, Jesus
    Perez-Cebolla, Francisco J.
    45TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2019), 2019, : 4525 - 4530