More Web Proxy on the site http://driver.im/

research-article

Few-Shot Cross Domain Battery Capacity Estimation

Authors:

Yang LiAuthors Info & Claims

UbiComp/ISWC '21 Adjunct: Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers

Pages 703 - 711

https://doi.org/10.1145/3460418.3480409

Published: 24 September 2021 Publication History

Abstract

Accurate capacity estimation is essential in a board range of battery applications. Because of the highly nonlinearity in the battery aging mechanism, recent works employ many supervised learning methods, which assume training and testing battery samples are generated from the same sample distribution. However, it is common for different battery data sets to have some extent of distribution shifts caused by different battery sizes, testing environments and historical load patterns. In this paper, we consider the scenario when only a few of labeled samples from the testing data set are available and formulate the battery estimation problem as a semi-supervised transfer learning problem. Inspired by JDOT, an unsupervised joint distribution domain adaptation algorithm based on optimal transport, we propose Semi-JDOT for regression problems where the source and the target label distributions have unequal supports. Our approach incorporates prior information of the labeled target samples as additional constraints and can be solved analytically. We conduct comprehensive experiments on a number of distinct battery data sets. The results show that the proposed approach outperforms existing supervised and semi-supervised methods by 10-30% under various few-shot experiment settings.

References

[1]

Tobias C. Bach, Simon F. Schuster, Elena Fleder, Jana Müller, Martin J. Brand, Henning Lorrmann, Andreas Jossen, and Gerhard Sextl. 2020. Nonlinear aging of cylindrical lithium-ion cells linked to heterogeneous compression. Journal of Energy Storage 5 (Jan. 2020), 212–223. https://doi.org/10.1016/j.est.2016.01.003

[2]

Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. 2006. Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples. Journal of Machine Learning Research 7, 85 (2006), 2399–2434. http://jmlr.org/papers/v7/belkin06a.html

Digital Library

[3]

Silvia Bobba, Fabrice Mathieux, Fulvio Ardente, Gian Andrea Blengini, Maria Anna Cusenza, Andreas Podias, and Andreas Pfrang. 2018. Life Cycle Assessment of repurposed electric vehicle batteries: an adapted method based on modelling energy flows. Journal of Energy Storage 19 (Aug. 2018), 213–225. https://doi.org/10.1016/j.est.2018.07.008

[4]

Hicham Chaoui, Navid Golbon, Imad Hmouz, Ridha Souissi, and Sofiene Tahar. 2015. Lyapunov-Based Adaptive State of Charge and State of Health Estimation for Lithium-Ion Batteries. IEEE Transactions on Industrial Electronics 62, 3 (Aug. 2015), 1610–1618. https://doi.org/10.1109/TIE.2014.2341576

[5]

Nicolas Courty, Rémi Flamary, Amaury Habrard, and Alain Rakotomamonjy. 2017. Joint distribution optimal transportation for domain adaptation. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc., 3730–3739. https://doi.org/abs/1705.08848

[6]

Nicolas Courty, Rémi Flamary, Devis Tuia, and Alain Rakotomamonjy. 2017. Optimal Transport for Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 9 (Sept. 2017), 1853–1865. https://doi.org/10.1109/TPAMI.2016.2615921

Digital Library

[7]

Marco Cuturi. 2013. Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In Advances in Neural Information Processing Systems, Vol. 26. Curran Associates, Inc., 2292–2300. https://proceedings.neurips.cc/paper/2013/file/af21d0c97db2e27e13572cbf59eb343d-Paper.pdf

[8]

Bharath Bhushan Damodaran, Benjamin Kellenberger, Rémi Flamary, Devis Tuia, and Nicolas Courty. 2018. DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IV(Lecture Notes in Computer Science, Vol. 11208), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 467–483. https://doi.org/10.1007/978-3-030-01225-0_28

Digital Library

[9]

Bruce Dunn, Haresh Kamath, and Jean-Marie Tarascon. 2011. Electrical Energy Storage for the Grid: A Battery of Choices. Science 334, 6058 (July 2011), 928–935. https://doi.org/10.1126/science.1212741

[10]

Aude Genevay, Marco Cuturi, Gabriel Peyré, and Francis Bach. 2016. Stochastic Optimization for Large-scale Optimal Transport. In Advances in Neural Information Processing Systems, Vol. 29. Curran Associates, Inc., 3440–3448. https://proceedings.neurips.cc/paper/2016/file/2a27b8144ac02f67687f76782a3b5d8f-Paper.pdf

[11]

Peiyao Guo, Ze Cheng, and Lei Yang. 2019. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction. Journal of Power Sources 412 (2019), 442–450. https://doi.org/10.1016/j.jpowsour.2018.11.072

[12]

Stephen J. Harris, David J. Harris, and Chen Li. 2017. Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells. Journal of Power Sources 342 (Dec. 2017), 589–597. https://doi.org/10.1016/j.jpowsour.2016.12.083

[13]

Chao Hu, Gaurav Jain, Craig Schmidt, Carrie Strief, and Melani Sullivan. 2015. Online estimation of lithium-ion battery capacity using sparse Bayesian learning. Journal of Power Sources 289, 6 (May 2015), 105–113. https://doi.org/10.3390/app6060166

[14]

Benjamin Jenkins, Ashish Krupadanam, and Anuradha M. Annaswamy. 2020. Fast Adaptive Observers for Battery Management Systems. IEEE Transactions on Control Systems Technology 28, 3 (Feb. 2020), 776–789. https://doi.org/10.1109/TIE.2014.2341576

[15]

Weihan Li, Yue Fan, Florian Ringbeck, Dominik Jöst, Xuebing Han, Minggao Ouyang, and Dirk Uwe Sauer. 2020. Model-Based Electrochemical Estimation and Constraint Management for Pulse Operation of Lithium Ion Batteries. Journal of Power Sources 476 (Aug. 2020), 228534. https://doi.org/10.1016/j.jpowsour.2020.228534

[16]

Yuanyuan Li, Hanmin Sheng, Yuhua Cheng, Daniel-Ioan Stroe, and Remus Teodorescu. 2020. State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis. Applied Energy 277 (July 2020), 115504. https://doi.org/10.1016/j.jpowsour.2017.05.004

[17]

Jeremy Neubauer and Ahmad Pesaran. 2007. The ability of battery second use strategies to impact plug-in electric vehicle prices and serve utility energy storage applications. Journal of Power Sources 196, 23 (June 2007), 10351–10358. https://doi.org/10.1016/j.jpowsour.2011.06.053

[18]

Sinno Jialin Pan, Ivor W. Tsang, James T. Kwok, and Qiang Yang. 2017. Domain Adaptation via Transfer Component Analysis. IEEE Transactions on Neural Networks 22, 2 (Feb. 2017), 199–210. https://doi.org/10.1109/TPAMI.2016.2615921

Digital Library

[19]

B. Saha and K. Goebel. 2007. Battery Data Set, NASA AMES Prognostics Data Repository. http://ti.arc.nasa.gov/project/prognostic-data-repository

[20]

Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, and Kate Saenko. 2010. Model-Based Electrochemical Estimation and Constraint Management for Pulse Operation of Lithium Ion Batteries. IEEE Transactions on Control Systems Technology 18, 3 (Sept. 2010), 654–663. https://doi.org/10.1109/TCST.2009.2027023

[21]

Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, and Kate Saenko. 2019. Semi-supervised Domain Adaptation via Minimax Entropy. 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (Feb. 2019), 8049–8057. https://doi.org/10.1109/ICCV.2019.00814

[22]

Sheng Shen, Mohammadkazem Sadoughi, Xiangyi Chen, Mingyi Hong, and Chao Hu. 2019. A deep learning method for online capacity estimation of lithium-ion batteries. Journal of Energy Storage 25 (2019), 100817. https://doi.org/10.1016/j.est.2019.100817

[23]

Fariborz Taherkhani, Hadi Kazemi, Ali Dabouei, Jeremy Dawson, and Nasser M Nasrabadi. 2020. Matching Distributions via Optimal Transport for Semi-Supervised Learning. arXiv preprint arXiv:2012.03790(2020).

[24]

Yuguang Yan, Wen Li, Hanrui Wu, Huaqing Min, Mingkui Tan, and Qingyao Wu. 2018. Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation. In IJCAI, Vol. 7. 2969–2975.

[25]

Xiao-Guang Yang, Yongjun Leng, Guangsheng Zhang, Shanhai Ge, and Chao-Yang Wang. 2017. Modeling of lithium plating induced aging of lithium-ion batteries: Transition from linear to nonlinear aging. Journal of Power Sources 360 (Aug. 2017), 28–40. https://doi.org/10.1016/j.jpowsour.2017.05.110

[26]

Zhi-Hua Zhou and Ming Li. 2005. Semi-Supervised Regression with Co-Training. In Proceedings of the 19th International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., 908–913. https://doi.org//dl.acm.org/doi/10.5555/1642293.1642439

Cited By

Tao SMa RZhao ZMa GSu LChang HChen YLiu HLiang ZCao TJi HHan ZLu MYang HWen ZYao JYu RWei GLi YZhang XXu TZhou G(2024)Generative learning assisted state-of-health estimation for sustainable battery recycling with random retirement conditionsNature Communications10.1038/s41467-024-54454-015:1Online publication date: 23-Nov-2024
https://doi.org/10.1038/s41467-024-54454-0
Lin CXu JMei X(2023)Improving state-of-health estimation for lithium-ion batteries via unlabeled charging dataEnergy Storage Materials10.1016/j.ensm.2022.10.03054(85-97)Online publication date: Jan-2023
https://doi.org/10.1016/j.ensm.2022.10.030
Ran ALiang ZChen SCheng MSun CMa FWang KLi BZhou GZhang XKang FWei G(2022)Fast Clustering of Retired Lithium-Ion Batteries for Secondary Life with a Two-Step Learning MethodACS Energy Letters10.1021/acsenergylett.2c018987:11(3817-3825)Online publication date: 11-Oct-2022
https://doi.org/10.1021/acsenergylett.2c01898

Recommendations

Transductive Multilabel Learning via Label Set Propagation

The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
Semantic guide for semi-supervised few-shot multi-label node classification
Abstract
We study a new research problem named semi-supervised few-shot multi-label node classification which has the following characteristics: 1) the extreme imbalance between the number of labeled and unlabeled nodes that are connected on ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

In multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

UbiComp/ISWC '21 Adjunct: Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers

September 2021

711 pages

ISBN:9781450384612

DOI:10.1145/3460418

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 September 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Tsinghua-Berkeley Shenzhen Institute Research Start-Up Funding
Shenzhen Science and Technology Program
Tsinghua SIGS Scientific Research Start-up Fund
Natural Science Foundation of China

Conference

UbiComp '21

Sponsor:

UbiComp '21: The 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing

September 21 - 26, 2021

Virtual, USA

Acceptance Rates

Overall Acceptance Rate 764 of 2,912 submissions, 26%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
257
Total Downloads

Downloads (Last 12 months)35
Downloads (Last 6 weeks)5

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Tao SMa RZhao ZMa GSu LChang HChen YLiu HLiang ZCao TJi HHan ZLu MYang HWen ZYao JYu RWei GLi YZhang XXu TZhou G(2024)Generative learning assisted state-of-health estimation for sustainable battery recycling with random retirement conditionsNature Communications10.1038/s41467-024-54454-015:1Online publication date: 23-Nov-2024
https://doi.org/10.1038/s41467-024-54454-0
Lin CXu JMei X(2023)Improving state-of-health estimation for lithium-ion batteries via unlabeled charging dataEnergy Storage Materials10.1016/j.ensm.2022.10.03054(85-97)Online publication date: Jan-2023
https://doi.org/10.1016/j.ensm.2022.10.030
Ran ALiang ZChen SCheng MSun CMa FWang KLi BZhou GZhang XKang FWei G(2022)Fast Clustering of Retired Lithium-Ion Batteries for Secondary Life with a Two-Step Learning MethodACS Energy Letters10.1021/acsenergylett.2c018987:11(3817-3825)Online publication date: 11-Oct-2022
https://doi.org/10.1021/acsenergylett.2c01898

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents