State-of-Health Estimation and Anomaly Detection in Li-Ion Batteries Based on a Novel Architecture with Machine Learning

被引:9
作者
Lee, Junghwan [1 ]
Sun, Huanli [1 ]
Liu, Yuxia [1 ]
Li, Xue [1 ]
Liu, Yixin [1 ]
Kim, Myungjun [2 ]
机构
[1] R&D Inst, FAW Grp, Changchun 130013, Peoples R China
[2] Chunbuk Natl Univ, Dept Comp Sci, Cheongju 28644, South Korea
来源
BATTERIES-BASEL | 2023年 / 9卷 / 05期
关键词
state of health; energy storage system; machine learning; DIAGNOSTICS;
D O I
10.3390/batteries9050264
中图分类号
O646 [电化学、电解、磁化学];
学科分类号
081704 ;
摘要
Variations across cells, modules, packs, and vehicles can cause significant errors in the state estimation of LIBs using machine learning algorithms, especially when trained with small datasets. Training with large datasets that account for all variations is often impractical due to resource and time constraints at initial product release. To address this issue, we proposed a novel architecture that leverages electronic control units, edge computers, and the cloud to detect unrevealed variations and abnormal degradations in LIBs. The architecture comprised a generalized deep neural network (DNN) for generalizability, a personalized DNN for accuracy within a vehicle, and a detector. We emphasized that a generalized DNN trained with small datasets must show reasonable estimation accuracy during cross validation, which is critical for real applications before online training. We demonstrated the feasibility of the architecture by conducting experiments on 65 DNN models, where we found distinct hyperparameter configurations. The results showed that the personalized DNN achieves a root mean square error (RMSE) of 0.33%, while the generalized DNN achieves an RMSE of 4.6%. Finally, the Mahalanobis distance was used to consider the SOH differences between the generalized DNN and personalized DNN to detect abnormal degradations.
引用
收藏
页数:23
相关论文
共 43 条
[1]   Hyperparameter Optimization: Comparing Genetic Algorithm against Grid Search and Bayesian Optimization [J].
Alibrahim, Hussain ;
Ludwig, Simone A. .
2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021), 2021, :1551-1559
[2]   Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis [J].
Alwosheel, Ahmad ;
van Cranenburgh, Sander ;
Chorus, Caspar G. .
JOURNAL OF CHOICE MODELLING, 2018, 28 :167-182
[3]   Degradation diagnostics for lithium ion cells [J].
Birkl, Christoph R. ;
Roberts, Matthew R. ;
McTurk, Euan ;
Bruce, Peter G. ;
Howey, David A. .
JOURNAL OF POWER SOURCES, 2017, 341 :373-386
[4]   A Convolutional Neural Network Approach for Estimation of Li-Ion Battery State of Health from Charge Profiles [J].
Chemali, Ephrem ;
Kollmeyer, Phillip J. ;
Preindl, Matthias ;
Fahmy, Youssef ;
Emadi, Ali .
ENERGIES, 2022, 15 (03)
[5]   Long Short-Term Memory Approach to Estimate Battery Remaining Useful Life Using Partial Data [J].
Chinomona, Benvolence ;
Chung, Chunhui ;
Chang, Lien-Kai ;
Su, Wei-Chih ;
Tsai, Mi-Ching .
IEEE ACCESS, 2020, 8 :165419-165431
[6]   The Mahalanobis distance [J].
De Maesschalck, R ;
Jouan-Rimbaud, D ;
Massart, DL .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2000, 50 (01) :1-18
[7]   Activation functions in deep learning: A comprehensive survey and benchmark [J].
Dubey, Shiv Ram ;
Singh, Satish Kumar ;
Chaudhuri, Bidyut Baran .
NEUROCOMPUTING, 2022, 503 :92-108
[8]   State of Health Estimation of Lithium-Ion Batteries in Electric Vehicles under Dynamic Load Conditions [J].
Ezemobi, Ethelbert ;
Silvagni, Mario ;
Mozaffari, Ahmad ;
Tonoli, Andrea ;
Khajepour, Amir .
ENERGIES, 2022, 15 (03)
[9]  
GLOROT X., 2011, P 14 INT C ARTIFICIA, P315
[10]   A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management [J].
Hasib, Shahid A. ;
Islam, S. ;
Chakrabortty, Ripon K. ;
Ryan, Michael J. ;
Saha, D. K. ;
Ahamed, Md H. ;
Moyeen, S., I ;
Das, Sajal K. ;
Ali, Md F. ;
Islam, Md R. ;
Tasneem, Z. ;
Badal, Faisal R. .
IEEE ACCESS, 2021, 9 :86166-86193