Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature

Datong Liu; Yue Luo; Yu Peng; Xiyuan Peng; Michael Pecht

Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature

Datong Liu
, Yue Luo
, Yu Peng
, Xiyuan Peng
, Michael Pecht

School of Electronics and Information Engineering

System Design Institute of Electro-Mechanic Engineering
University of Maryland, College Park

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

45 Scopus citations

Abstract

Long term prediction such as multi-step time series prediction is a challenging prognostics problem. This paper proposes an improved AR time series model called ND-AR model (Nonlinear Degradation AutoRegression) for Remaining Useful Life (RUL) estimation of lithium-ion batteries. The nonlinear degradation feature of the lithiumion battery capacity degradation is analyzed and then the non-linear accelerated degradation factor is extracted to improve the linear AR model. In this model, the nonlinear degradation factor can be obtained with curve fitting, and then the ND-AR model can be applied as an adaptive datadriven prognostics method to monitor degradation time series data. Experimental results with CALCE battery data set show that the proposed nonlinear degradation AR model can realize satisfied prognostics for various lithium-ion batteries with low computing complexity.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012
Editors	Indranil Roychoudhury, Jose R. Celaya, Abhinav Saxena
Publisher	Prognostics and Health Management Society
Pages	336-342
Number of pages	7
ISBN (Electronic)	9781936263059
State	Published - 2012
Event	2012 Annual Conference of the Prognostics and Health Management Society, PHM 2012 - Minneapolis, United States Duration: 23 Sep 2012 → 27 Sep 2012

Publication series

Name	Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012

Conference

Conference	2012 Annual Conference of the Prognostics and Health Management Society, PHM 2012
Country/Territory	United States
City	Minneapolis
Period	23/09/12 → 27/09/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Cite this

Liu, D., Luo, Y., Peng, Y., Peng, X., & Pecht, M. (2012). Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature. In I. Roychoudhury, J. R. Celaya, & A. Saxena (Eds.), Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012 (pp. 336-342). (Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012). Prognostics and Health Management Society.

Liu, Datong ; Luo, Yue ; Peng, Yu et al. / Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature. Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012. editor / Indranil Roychoudhury ; Jose R. Celaya ; Abhinav Saxena. Prognostics and Health Management Society, 2012. pp. 336-342 (Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012).

@inproceedings{4370297f60054867b281c80c8b4f5c72,

title = "Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature",

abstract = "Long term prediction such as multi-step time series prediction is a challenging prognostics problem. This paper proposes an improved AR time series model called ND-AR model (Nonlinear Degradation AutoRegression) for Remaining Useful Life (RUL) estimation of lithium-ion batteries. The nonlinear degradation feature of the lithiumion battery capacity degradation is analyzed and then the non-linear accelerated degradation factor is extracted to improve the linear AR model. In this model, the nonlinear degradation factor can be obtained with curve fitting, and then the ND-AR model can be applied as an adaptive datadriven prognostics method to monitor degradation time series data. Experimental results with CALCE battery data set show that the proposed nonlinear degradation AR model can realize satisfied prognostics for various lithium-ion batteries with low computing complexity.",

author = "Datong Liu and Yue Luo and Yu Peng and Xiyuan Peng and Michael Pecht",

year = "2012",

language = "英语",

series = "Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012",

publisher = "Prognostics and Health Management Society",

pages = "336--342",

editor = "Indranil Roychoudhury and Celaya, \{Jose R.\} and Abhinav Saxena",

booktitle = "Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012",

address = "美国",

note = "2012 Annual Conference of the Prognostics and Health Management Society, PHM 2012 ; Conference date: 23-09-2012 Through 27-09-2012",

}

Liu, D, Luo, Y, Peng, Y , Peng, X & Pecht, M 2012, Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature. in I Roychoudhury, JR Celaya & A Saxena (eds), Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012. Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012, Prognostics and Health Management Society, pp. 336-342, 2012 Annual Conference of the Prognostics and Health Management Society, PHM 2012, Minneapolis, United States, 23/09/12.

Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature. / Liu, Datong; Luo, Yue; Peng, Yu et al.
Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012. ed. / Indranil Roychoudhury; Jose R. Celaya; Abhinav Saxena. Prognostics and Health Management Society, 2012. p. 336-342 (Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature

AU - Liu, Datong

AU - Luo, Yue

AU - Peng, Yu

AU - Peng, Xiyuan

AU - Pecht, Michael

PY - 2012

Y1 - 2012

N2 - Long term prediction such as multi-step time series prediction is a challenging prognostics problem. This paper proposes an improved AR time series model called ND-AR model (Nonlinear Degradation AutoRegression) for Remaining Useful Life (RUL) estimation of lithium-ion batteries. The nonlinear degradation feature of the lithiumion battery capacity degradation is analyzed and then the non-linear accelerated degradation factor is extracted to improve the linear AR model. In this model, the nonlinear degradation factor can be obtained with curve fitting, and then the ND-AR model can be applied as an adaptive datadriven prognostics method to monitor degradation time series data. Experimental results with CALCE battery data set show that the proposed nonlinear degradation AR model can realize satisfied prognostics for various lithium-ion batteries with low computing complexity.

AB - Long term prediction such as multi-step time series prediction is a challenging prognostics problem. This paper proposes an improved AR time series model called ND-AR model (Nonlinear Degradation AutoRegression) for Remaining Useful Life (RUL) estimation of lithium-ion batteries. The nonlinear degradation feature of the lithiumion battery capacity degradation is analyzed and then the non-linear accelerated degradation factor is extracted to improve the linear AR model. In this model, the nonlinear degradation factor can be obtained with curve fitting, and then the ND-AR model can be applied as an adaptive datadriven prognostics method to monitor degradation time series data. Experimental results with CALCE battery data set show that the proposed nonlinear degradation AR model can realize satisfied prognostics for various lithium-ion batteries with low computing complexity.

UR - https://www.scopus.com/pages/publications/84920541505

M3 - 会议稿件

AN - SCOPUS:84920541505

T3 - Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012

SP - 336

EP - 342

BT - Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012

A2 - Roychoudhury, Indranil

A2 - Celaya, Jose R.

A2 - Saxena, Abhinav

PB - Prognostics and Health Management Society

T2 - 2012 Annual Conference of the Prognostics and Health Management Society, PHM 2012

Y2 - 23 September 2012 through 27 September 2012

ER -

Liu D, Luo Y, Peng Y , Peng X, Pecht M. Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature. In Roychoudhury I, Celaya JR, Saxena A, editors, Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012. Prognostics and Health Management Society. 2012. p. 336-342. (Proceedings of the Annual Conference of the Prognostics and Health Management Society 2012, PHM 2012).

Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this