journal article·2022-09Open access

Data‐driven battery degradation prediction: Forecasting voltage‐capacity curves using one‐cycle data

Jinpeng Tian, Rui Xiong, Weixiang Shen, Jiahuan Lu

EcoMat· Volume 4· Issue 5

Abstract

Abstract With the wide deployment of rechargeable batteries, battery degradation prediction has emerged as a challenging issue. However, battery life defined by capacity loss provides limited information regarding battery degradation. In this article, we explore the prediction of voltage‐capacity curves over battery lifetime based on a sequence to sequence (seq2seq) model. We demonstrate that the data of one present voltage‐capacity curve can be used as the input of the seq2seq model to accurately predict the voltage‐capacity curves at 100, 200, and 300 cycles ahead. This offers an opportunity to update battery management strategies in response to the predicted consequences. Besides, the model avoids feature engineering and is flexible to incorporate different numbers of input and output cycles. Therefore, it can be easily transplanted to other battery systems or electrochemical components. Furthermore, the model features data generation, that is, we can use the data of only one cycle to generate a large spectrum of aging data at the future cycles for developing other battery diagnosis or prognosis methods. In this way, the time and energy consuming battery degradation tests can be sharply reduced.image
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Electric Vehicles and Infrastructure

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Vehicle Engineering, School of Mechanical Engineering Beijing Institute of Technology Beijing China

Faculty of Science, Engineering and Technology Swinburne University of Technology Hawthorn Victoria Australia

Funding

National Science Foundation

References (59)

Show source-provided references
1. 10.1038/nchem.208510.1038/nchem.2085 ↗
2. 10.1002/eom2.1201910.1002/eom2.12019 ↗
3. 10.1002/inf2.1200010.1002/inf2.12000 ↗
4. 10.1016/j.joule.2020.01.01310.1016/j.joule.2020.01.013 ↗
5. 10.1126/science.125329210.1126/science.1253292 ↗
6. 10.1016/j.ensm.2021.02.01810.1016/j.ensm.2021.02.018 ↗
7. 10.1016/j.joule.2019.11.01810.1016/j.joule.2019.11.018 ↗
8. 10.1016/j.joule.2021.06.00510.1016/j.joule.2021.06.005 ↗
9. 10.1016/j.rser.2019.10925410.1016/j.rser.2019.109254 ↗
10. 10.1016/j.apenergy.2019.11381810.1016/j.apenergy.2019.113818 ↗
11. 10.1016/j.jpowsour.2011.08.04010.1016/j.jpowsour.2011.08.040 ↗
12. 10.1016/j.microrel.2012.12.00410.1016/j.microrel.2012.12.004 ↗
13. 10.1149/1.180481210.1149/1.1804812 ↗
14. 10.1002/er.500210.1002/er.5002 ↗
15. 10.1016/j.jpowsour.2017.05.00410.1016/j.jpowsour.2017.05.004 ↗
16. 10.1016/j.jpowsour.2013.03.12910.1016/j.jpowsour.2013.03.129 ↗
17. 10.1109/TVT.2018.280518910.1109/TVT.2018.2805189 ↗
18. 10.1016/j.egyai.2020.10000610.1016/j.egyai.2020.100006 ↗
19. 10.1016/j.apenergy.2019.11384110.1016/j.apenergy.2019.113841 ↗
20. 10.1016/j.est.2015.05.00310.1016/j.est.2015.05.003 ↗
21. 10.1038/s41560‐019‐0356‐810.1038/s41560‐019‐0356‐8 ↗
22. 10.1002/inf2.1209410.1002/inf2.12094 ↗
23. 10.1002/anie.20210736910.1002/anie.202107369 ↗
24. 10.1016/j.joule.2021.10.01010.1016/j.joule.2021.10.010 ↗
25. 10.1016/j.joule.2021.09.01510.1016/j.joule.2021.09.015 ↗
26. 10.1016/j.ress.2020.10739610.1016/j.ress.2020.107396 ↗
27. 10.1016/j.jpowsour.2020.22865410.1016/j.jpowsour.2020.228654 ↗
28. 10.1038/s41467‐020‐15235‐710.1038/s41467‐020‐15235‐7 ↗
29. 10.1016/j.apenergy.2020.11564610.1016/j.apenergy.2020.115646 ↗
30. 10.1016/j.apenergy.2021.11813410.1016/j.apenergy.2021.118134 ↗
31. 10.1016/j.jpowsour.2020.22880610.1016/j.jpowsour.2020.228806 ↗
32. 10.1016/j.rser.2019.05.04210.1016/j.rser.2019.05.042 ↗
33. 10.1016/j.rser.2019.10946410.1016/j.rser.2019.109464 ↗
34. 10.1016/j.etran.2019.10001110.1016/j.etran.2019.100011 ↗
35. 10.1016/j.joule.2021.05.01210.1016/j.joule.2021.05.012 ↗
36. 10.1016/j.jpowsour.2013.11.02910.1016/j.jpowsour.2013.11.029 ↗
37. 10.1038/s41586‐020‐1994‐510.1038/s41586‐020‐1994‐5 ↗
38. 10.1016/j.est.2019.10081710.1016/j.est.2019.100817 ↗
39. 10.3390/en1215291010.3390/en12152910 ↗
40. Sequence to sequence learning with neural networks
41. 10.1162/neco.1997.9.8.173510.1162/neco.1997.9.8.1735 ↗
42. 10.1016/j.apenergy.2018.09.18210.1016/j.apenergy.2018.09.182 ↗
43. 10.1038/s42256‐020‐0156‐710.1038/s42256‐020‐0156‐7 ↗
44. 10.1016/j.egyai.2021.10008110.1016/j.egyai.2021.100081 ↗
45. 10.1149/1945‐7111/ac2d3e10.1149/1945‐7111/ac2d3e ↗
46. BirklC.Oxford battery degradation dataset 1. Published Online;2017. doi:10.5287/bodleian:KO2kdmYGg
47. 10.1016/j.joule.2019.07.02610.1016/j.joule.2019.07.026 ↗
48. 10.1016/j.ensm.2021.07.01610.1016/j.ensm.2021.07.016 ↗
49. 10.1002/batt.20210016610.1002/batt.202100166 ↗
50. 10.1016/j.eng.2020.08.01510.1016/j.eng.2020.08.015 ↗
51. 10.1016/j.mtener.2020.10053710.1016/j.mtener.2020.100537 ↗
52. 10.1109/TKDE.2009.19110.1109/TKDE.2009.191 ↗
53. 10.1016/j.joule.2021.11.00610.1016/j.joule.2021.11.006 ↗
54. 10.1016/j.egyai.2020.10001610.1016/j.egyai.2020.100016 ↗
55. 10.1016/j.est.2021.10244010.1016/j.est.2021.102440 ↗
56. 10.1016/j.apenergy.2021.11681210.1016/j.apenergy.2021.116812 ↗
57. LuongT PhamH ManningCD.Effective approaches to attention‐based neural machine translation. In:Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics;2015:1412–1421. doi:10.18653/v1/D15‐116610.18653/v1/D15-1166 ↗
58. KingmaDP BaJ.Adam: A Method for Stochastic Optimization.3rd Int Conf Learn Represent ICLR 2015–Conf Track Proc. Published online December 22 2014:1–15.http://arxiv.org/abs/1412.6980
59. CholletF.Others. Keras. Published online;2015.