Battery internal short circuit diagnosis based on vision transformer without real data

Hongchang Cai; Xuyang Liu; Lin Sun; Yuwen Xu; Yanan Wang; Xuebing Han; Yuejiu Zheng; Yuedong Sun; Minggao Ouyang

doi:10.59717/j.xinn-energy.2024.100041

The Innovation Energy > 2024 Vol. 1 > No. 3 > 100041

Next Article Previous Article

ARTICLE Open Access

Cite PDF

Battery internal short circuit diagnosis based on vision transformer without real data

1.
School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2.
State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China
3.
These authors contributed equally

More Information

Corresponding author: yuejiu.zheng@usst.edu.cn
Received Date: May 30, 2024

Accepted Date: July 22, 2024

Published Online: August 15, 2024

The Innovation Energy 1(3), https://doi.org/10.59717/j.xinn-energy.2024.100041 | Cite this article

GRAPHICAL ABSTRACT

GRAPHICAL ABSTRACT

DownLoad: Full size image

PUBLIC SUMMARY

PUBLIC SUMMARY
1. Developing AI models for ISC diagnosis in lithium-ion batteries is challenging due to limited fault data.
  
  By extracting features from a mechanism model, AI model construction is achieved using only virtual data features.
  
  When applied to real ISC data, the model demonstrates high accuracy, robustness, and generalization.

ABSTRACT

ABSTRACT

The diagnosis of an internal short circuit (ISC) fault is an integral part of thermal runaway warning for lithium-ion batteries. A higher level of accuracy in ISC fault diagnosis needs an artificial intelligence model, but lack of fault data and label ambiguity present challenges. To address these demands and challenges, features are extracted using a mean difference model to amplify the difference between fault data and normal data, while reduce the inherent error between virtual data and real data. Additionally, the model considers the influence of other faults and the variability within the real data. The Vision Transformer model is then trained with only this virtual feature to achieve 100% accuracy when verifying real ISC fault data under constant current charging condition. By breaking away from the reliance on real fault data for modeling, this approach greatly reduces the cost of human labor, materials, time, and carbon emissions, and also provides a reference for other projects facing similar challenges.

FullText(HTML)

REFERENCES

[1]	Yin, H., Ma, S., Li, H., et al. (2021). Modeling strategy for progressive failure prediction in lithium-ion batteries under mechanical abuse. eTransportation 7: 100098. DOI: 10.1016/j.etran.2020.100098. View in Article CrossRef Google Scholar Scopus
[2]	Li, C., Wu, Y., Li, X., et al. (2024). Flame-retardant composite phase change material with silicone resin and melamine phosphate for battery thermal safety. The Innovation Energy 1: 100021. DOI: 10.59717/j.xinn-energy.2024.100021. View in Article CrossRef Google Scholar Scopus
[3]	Ren, D., Feng, X., Liu, L., et al. (2021). Investigating the relationship between internal short circuit and thermal runaway of lithium-ion batteries under thermal abuse condition. Energy Storage Mater. 34: 563−573. DOI: 10.1016/j.ensm.2020.10.020. View in Article CrossRef Google Scholar Scopus
[4]	Wang, Y., Zhang, X., Li, K., et al. (2023). Perspectives and challenges for future lithium-ion battery control and management. eTransportation 18: 100260. DOI: 10.1016/j.etran.2023.100260. View in Article CrossRef Google Scholar Scopus
[5]	Abaza, A., Ferrari, S., Wong, H.K., et al. (2018). Experimental study of internal and external short circuits of commercial automotive pouch lithium-ion cells. J. Energy Storage. 16: 211−217. DOI: 10.1016/j.est.2018.01.015. View in Article CrossRef Google Scholar Scopus
[6]	Wang, H., Simunovic, S., Maleki, H., et al. (2016). Internal configuration of prismatic lithium-ion cells at the onset of mechanically induced short circuit. J. Power Sources. 306: 424−430. DOI: 10.1016/j.jpowsour.2015.12.026. View in Article CrossRef Google Scholar Scopus
[7]	Sun, Y., Yuan, Y., Lu, L., et al. (2022). A comprehensive research on internal short circuits caused by copper particle contaminants on cathode in lithium-ion batteries. eTransportation 13: 100183. DOI: 10.1016/j.etran.2022.100183. View in Article CrossRef Google Scholar Scopus
[8]	Meng, J., Yue, M., and Diallo, D. (2023). Nonlinear extension of battery constrained predictive charging control with transmission of jacobian matrix. Int. J. Elec. Power. 146: 108762. DOI: 10.1016/j.ijepes.2022.108762. View in Article CrossRef Google Scholar
[9]	Kong, D., Lv, H., Ping, P., et al. (2023). A review of early warning methods of thermal runaway of lithium ion batteries. J. Energy Storage 64: 107073. DOI: 10.1016/j.est.2023.107073. View in Article CrossRef Google Scholar Scopus
[10]	Lyu, P., Liu, X., Qu, J., et al. (2020). Recent advances of thermal safety of lithium ion battery for energy storage. Energy Storage Mater. 31: 195−220. DOI: 10.1016/j.ensm.2020.06.042. View in Article CrossRef Google Scholar Scopus
[11]	Feng, X., Ouyang, M., Liu, X., et al. (2018). Thermal runaway mechanism of lithium ion battery for electric vehicles: A review. Energy Storage Mater. 10: 246−267. DOI: 10.1016/j.ensm.2017.05.013. View in Article CrossRef Google Scholar Scopus
[12]	Xiong, R., Ma, S., Li, H., et al. (2020). Toward a safer battery management system: A critical review on diagnosis and prognosis of battery short circuit. iScience 23: 101010. DOI: 10.1016/j.isci.2020.101010. View in Article CrossRef Google Scholar
[13]	Qiao, D., Wei, X., Jiang, B., et al. (2024). Data-driven fault diagnosis of internal short circuit for series-connected battery packs using partial voltage curves. IEEE T. Ind. Inform. 20: 6751−6761. DOI: 10.1109/TII.2024.3353872. View in Article CrossRef Google Scholar
[14]	Jia, Y.K., Li, J.N., Yuan, C.H., et al. (2021). Data-driven safety risk prediction of lithium-ion battery. Adv. Energy Mater. 11: 2003868. DOI: 10.1002/aenm.202003868. View in Article CrossRef Google Scholar
[15]	Jia, Y. and Xu, J. (2023). Data-driven short circuit resistance estimation in battery safety issues. J. Energy Chem. 79: 37−44. DOI: 10.1016/j.jechem.2022.12.035. View in Article CrossRef Google Scholar Scopus
[16]	Samanta, A., Chowdhuri, S., and Williamson, S.S. (2021). Machine learning-based data-driven fault detection/diagnosis of lithium-ion battery: A critical review. Electronics 10: 1309. DOI: 10.3390/electronics10111309. View in Article CrossRef Google Scholar Scopus
[17]	Kong, X.D., Zheng, Y.J., Ouyang, M.G., et al. (2018). Fault diagnosis and quantitative analysis of micro-short circuits for lithium-ion batteries in battery packs. J. Power Sources 395: 358−368. DOI: 10.1016/j.jpowsour.2018.05.097. View in Article CrossRef Google Scholar Scopus
[18]	Qiao, D.D., Wang, X.Y., Lai, X., et al. (2022). Online quantitative diagnosis of internal short circuit for lithium-ion batteries using incremental capacity method. Energy 243: 123082. DOI: 10.1016/j.energy.2021.123082. View in Article CrossRef Google Scholar Scopus
[19]	Qiao, D., Wei, X., Jiang, B., et al. (2024). Quantitative diagnosis of internal short circuit for lithium-ion batteries using relaxation voltage. IEEE T. Ind. Electron. 71: 13201−13210. DOI: 10.1109/TIE.2023.3342289. View in Article CrossRef Google Scholar
[20]	Xue, Q., Li, G., Zhang, Y., et al. (2021). Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution. J. Power Sources 482: 228964. DOI: 10.1016/j.jpowsour.2020.228964. View in Article CrossRef Google Scholar Scopus
[21]	Wang, G., Zhao, J., Yang, J., et al. (2023). Multivariate statistical analysis based cross voltage correlation method for internal short-circuit and sensor faults diagnosis of lithium-ion battery system. J. Energy Storage 62: 106978. DOI: 10.1016/j.est.2023.106978. View in Article CrossRef Google Scholar Scopus
[22]	Sun, Z., Wang, Z., Chen, Y., et al. (2022). Modified relative entropy-based lithium-ion battery pack online short-circuit detection for electric vehicle. IEEE T. Transp. Electr. 8: 1710−1723. DOI: 10.1109/TTE.2021.3128048. View in Article CrossRef Google Scholar
[23]	Wang, G., Yang, J., and Jiao, J. (2023). Voltage correlation-based principal component analysis method for short circuit fault diagnosis of series battery pack. IEEE T. Ind. Electron. 70: 9025−9034. DOI: 10.1109/TIE.2022.3210588. View in Article CrossRef Google Scholar
[24]	Xia, B., Shang, Y., Nguyen, T., et al. (2017). A correlation based fault detection method for short circuits in battery packs. J. Power Sources 337: 1−10. DOI: 10.1016/j.jpowsour.2016.11.007. View in Article CrossRef Google Scholar Scopus
[25]	Feng, X.N., Pan, Y., He, X.M., et al. (2018). Detecting the internal short circuit in large-format lithium-ion battery using model-based fault-diagnosis algorithm. J. Energy Storage 18: 26−39. DOI: 10.1016/j.est.2018.04.020. View in Article CrossRef Google Scholar Scopus
[26]	Hu, J., He, H., Wei, Z., et al. (2022). Disturbance-immune and aging-robust internal short circuit diagnostic for lithium-ion battery. IEEE T. Ind. Electron. 69: 1988−1999. DOI: 10.1109/tie.2021.3063968. View in Article CrossRef Google Scholar
[27]	Deng, J., Bae, C., Marcicki, J., et al. (2018). Safety modelling and testing of lithium-ion batteries in electrified vehicles. Nat. Energy 3: 261−266. DOI: 10.1038/s41560-018-0122-3. View in Article CrossRef Google Scholar Scopus
[28]	Ma, R., Deng, Y., and Wang, X. (2023). Simplified electrochemical model assisted detection of the early-stage internal short circuit through battery aging. J. Energy Storage 66: 107478. DOI: 10.1016/j.est.2023.107478. View in Article CrossRef Google Scholar Scopus
[29]	Meng, J.W., Boukhnifer, M., and Diallo, D. (2019). On-line model-based short circuit diagnosis of lithium-ion batteries for electric vehicle application. 45th Annual Conference of the IEEE Industrial Electronics Society (IECON 2019) 1:6022-6027. DOI: 10.1109/IECON.2019.8927671. View in Article Google Scholar
[30]	Mariani, M.M., Machado, I., Magrelli, V., et al. (2023). Artificial intelligence in innovation research: A systematic review, conceptual framework, and future research directions. Technovation 122: 102623. DOI: 10.1016/j.technovation.2022.102623. View in Article CrossRef Google Scholar Scopus
[31]	Wang, Y., Tian, J., Sun, Z., et al. (2020). A comprehensive review of battery modeling and state estimation approaches for advanced battery management systems. Renew. Sust. Energ. Rev. 131: 110015. DOI: 10.1016/j.rser.2020.110015. View in Article CrossRef Google Scholar Scopus
[32]	Zhang, X., Li, Z., Luo, L., et al. (2022). A review on thermal management of lithium-ion batteries for electric vehicles. Energy 238: 121652. DOI: 10.1016/j.energy.2021.121652. View in Article CrossRef Google Scholar Scopus
[33]	Wang, Y., Wang, L., Li, M., et al. (2020). A review of key issues for control and management in battery and ultra-capacitor hybrid energy storage systems. eTransportation 4: 100064. DOI: 10.1016/j.etran.2020.100064. View in Article CrossRef Google Scholar Scopus
[34]	Liang, Y., Emadi, A., Gross, O., et al. (2022). A comparative study between physics, electrical and data driven lithium-ion battery voltage modeling approaches. SAE Tech. Pap. 2022-2001-0700. DOI: 10.4271/2022-01-0700. View in Article Google Scholar
[35]	Hossain Lipu, M.S., Hannan, M.A., Karim, T.F., et al. (2021). Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlook. J. Cleaner Prod. 292: 126044. DOI: 10.1016/j.jclepro.2021.126044. View in Article CrossRef Google Scholar Scopus
[36]	Zhang, X., Chen, S., Zhu, J.Z., et al. (2023). A critical review of thermal runaway prediction and early-warning methods for lithium-ion batteries. Energy Mater. Adv. 4: 0008. DOI: 10.34133/energymatadv.0008. View in Article CrossRef Google Scholar
[37]	Finegan, D.P., Zhu, J.E., Feng, X.N., et al. (2021). The application of data-driven methods and physics-based learning for improving battery safety. Joule 5: 316−329. DOI: 10.1016/j.joule.2020.11.018. View in Article CrossRef Google Scholar
[38]	Sun, Z., Wang, Z., Liu, P., et al. (2021). Overview of fault diagnosis in new energy vehicle power battery system. Chin. J. Mech. Eng. (Engl. Ed.) 57: 87−104. DOI: 10.3901/JME.2021.14.087. View in Article CrossRef Google Scholar
[39]	Schmid, M., Kleiner, J., and Endisch, C. (2022). Early detection of internal short circuits in series-connected battery packs based on nonlinear process monitoring. J. Energy Storage 48: 103732. DOI: 10.1016/j.est.2021.103732. View in Article CrossRef Google Scholar
[40]	Liu, H., Hao, S., Han, T., et al. (2023). Random forest-based online detection and location of internal short circuits in lithium battery energy storage systems with limited number of sensors. IEEE T. Instrum. Meas. 72: 1−11. DOI: 10.1109/TIM.2023.3304674. View in Article CrossRef Google Scholar
[41]	Xie, J.L., Zhang, L., Yao, T.Q., et al. (2020). Quantitative diagnosis of internal short circuit for cylindrical li-ion batteries based on multiclass relevance vector machine. J. Energy Storage 32: 101957. DOI: 10.1016/j.est.2020.101957. View in Article CrossRef Google Scholar Scopus
[42]	Cui, B., Wang, H., Li, R., et al. (2023). Internal short circuit early detection of lithium-ion batteries from impedance spectroscopy using deep learning. J. Power Sources 563: 232824. DOI: 10.1016/j.jpowsour.2023.232824. View in Article CrossRef Google Scholar Scopus
[43]	Lu, X., Qiu, J., Lei, G., et al. (2023). State of health estimation of lithium iron phosphate batteries based on degradation knowledge transfer learning. IEEE T. Transp. Electr. 9: 4692−4703. DOI: 10.1109/TTE.2023.3240617. View in Article CrossRef Google Scholar
[44]	Su, S., Li, W., Mou, J., et al. (2023). A hybrid battery equivalent circuit model, deep learning, and transfer learning for battery state monitoring. IEEE T. Transp. Electr. 9: 1113−1127. DOI: 10.1109/TTE.2022.3204843. View in Article CrossRef Google Scholar
[45]	Dong, Z.K., Ji, X.Y., Wang, J.Y., et al. (2024). Icncs: Internal cascaded neuromorphic computing system for fast electric vehicle state-of-charge estimation. IEEE T. Consum. Electr. 70: 4311−4320. DOI: 10.1109/TCE.2023.3257201. View in Article CrossRef Google Scholar
[46]	Cai, L.H., Wang, H., Dong, Z.K., et al. (2023). A multi-fault diagnostic method based on category-reinforced domain adaptation network for series-connected battery packs. J. Energy Storage 60: 106690. DOI: 10.1016/j.est.2023.106690. View in Article CrossRef Google Scholar Scopus
[47]	Wang, H., Nie, J.H., He, Z.W., et al. (2023). A reconstruction-based model with transformer and long short-term memory for internal short circuit detection in battery packs. Energy Rep. 9: 2420−2430. DOI: 10.1016/j.egyr.2023.01.092. View in Article CrossRef Google Scholar Scopus

Cited by

ABOUT THIS ARTICLE

Cite this article:

Cai H., Liu X., Sun L., et al., (2024). Battery internal short circuit diagnosis based on vision transformer without real data. The Innovation Energy 1(3): 100041. https://doi.org/10.59717/j.xinn-energy.2024.100041

Cai H., Liu X., Sun L., et al., (2024). Battery internal short circuit diagnosis based on vision transformer without real data. The Innovation Energy 1(3): 100041. https://doi.org/10.59717/j.xinn-energy.2024.100041

Welcome!

To request copyright permission to republish or share portions of our works, please visit Copyright Clearance Center's (CCC) Marketplace website at marketplace.copyright.com.

Standard PDF

Extended PDF

Figures(6) Tables(2)

Article Metrics

Article views(7470) PDF downloads(10823)

Battery internal short circuit diagnosis based on vision transformer without real data

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

{{newsColumn.name}}

Official Account

{{newsColumn.name}}

Stay connected

{{newsColumn.name}}

Battery internal short circuit diagnosis based on vision transformer without real data

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

Export File

Citation

Format

Content

{{newsColumn.name}}

Official Account

{{newsColumn.name}}

Stay connected

{{newsColumn.name}}