skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on March 25, 2020

Title: Data-driven prediction of battery cycle life before capacity degradation

Abstract

Accurately predicting the lifetime of complex, nonlinear systems such as lithium-ion batteries is critical for accelerating technology development. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. We generate a comprehensive dataset consisting of 124 commercial lithium iron phosphate/graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2,300 cycles. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine-learning tools to both predict and classify cells by cycle life. Our best models achieve 9.1% test error for quantitatively predicting cycle life using the first 100 cycles (exhibiting a median increase of 0.2% from initial capacity) and 4.9% test error using the first 5 cycles for classifying cycle life into two groups. This work highlights the promise of combining deliberate data generation with data-driven modelling to predict the behaviour of complex dynamical systems.

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [3]; ORCiD logo [2]; ORCiD logo [4]; ORCiD logo [4]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [5]; ORCiD logo [2]; ORCiD logo [1]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Chemical Engineering
  2. Stanford Univ., CA (United States). Dept. of Materials Science and Engineering
  3. Univ. of Michigan, Ann Arbor, MI (United States). Dept. of Electrical Engineering and Computer Science
  4. Toyota Research Inst., Los Altos, CA (United States)
  5. Stanford Univ., CA (United States). Dept. of Materials Science and Engineering; Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Chemical Engineering
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office (EE-3V)
OSTI Identifier:
1526566
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Accepted Manuscript
Journal Name:
Nature Energy
Additional Journal Information:
Journal Volume: 4; Journal Issue: 5; Journal ID: ISSN 2058-7546
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
25 ENERGY STORAGE; 42 ENGINEERING

Citation Formats

Severson, Kristen A., Attia, Peter M., Jin, Norman, Perkins, Nicholas, Jiang, Benben, Yang, Zi, Chen, Michael H., Aykol, Muratahan, Herring, Patrick K., Fraggedakis, Dimitrios, Bazant, Martin Z., Harris, Stephen J., Chueh, William C., and Braatz, Richard D. Data-driven prediction of battery cycle life before capacity degradation. United States: N. p., 2019. Web. doi:10.1038/s41560-019-0356-8.
Severson, Kristen A., Attia, Peter M., Jin, Norman, Perkins, Nicholas, Jiang, Benben, Yang, Zi, Chen, Michael H., Aykol, Muratahan, Herring, Patrick K., Fraggedakis, Dimitrios, Bazant, Martin Z., Harris, Stephen J., Chueh, William C., & Braatz, Richard D. Data-driven prediction of battery cycle life before capacity degradation. United States. doi:10.1038/s41560-019-0356-8.
Severson, Kristen A., Attia, Peter M., Jin, Norman, Perkins, Nicholas, Jiang, Benben, Yang, Zi, Chen, Michael H., Aykol, Muratahan, Herring, Patrick K., Fraggedakis, Dimitrios, Bazant, Martin Z., Harris, Stephen J., Chueh, William C., and Braatz, Richard D. Mon . "Data-driven prediction of battery cycle life before capacity degradation". United States. doi:10.1038/s41560-019-0356-8.
@article{osti_1526566,
title = {Data-driven prediction of battery cycle life before capacity degradation},
author = {Severson, Kristen A. and Attia, Peter M. and Jin, Norman and Perkins, Nicholas and Jiang, Benben and Yang, Zi and Chen, Michael H. and Aykol, Muratahan and Herring, Patrick K. and Fraggedakis, Dimitrios and Bazant, Martin Z. and Harris, Stephen J. and Chueh, William C. and Braatz, Richard D.},
abstractNote = {Accurately predicting the lifetime of complex, nonlinear systems such as lithium-ion batteries is critical for accelerating technology development. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. We generate a comprehensive dataset consisting of 124 commercial lithium iron phosphate/graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2,300 cycles. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine-learning tools to both predict and classify cells by cycle life. Our best models achieve 9.1% test error for quantitatively predicting cycle life using the first 100 cycles (exhibiting a median increase of 0.2% from initial capacity) and 4.9% test error using the first 5 cycles for classifying cycle life into two groups. This work highlights the promise of combining deliberate data generation with data-driven modelling to predict the behaviour of complex dynamical systems.},
doi = {10.1038/s41560-019-0356-8},
journal = {Nature Energy},
number = 5,
volume = 4,
place = {United States},
year = {2019},
month = {3}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on March 25, 2020
Publisher's Version of Record

Citation Metrics:
Cited by: 20 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

A Mechanical Aging Mechanism in Lithium-Ion Batteries
journal, January 2014

  • Waldmann, T.; Gorse, S.; Samtleben, T.
  • Journal of The Electrochemical Society, Vol. 161, Issue 10
  • DOI: 10.1149/2.1001410jes

Understanding Lithium Inventory Loss and Sudden Performance Fade in Cylindrical Cells during Cycling with Deep-Discharge Steps
journal, December 2014

  • Sarasketa-Zabala, E.; Aguesse, F.; Villarreal, I.
  • The Journal of Physical Chemistry C, Vol. 119, Issue 2
  • DOI: 10.1021/jp510071d

Performance and cost of materials for lithium-based rechargeable automotive batteries
journal, April 2018


Influence of Cell Design on Temperatures and Temperature Gradients in Lithium-Ion Cells: An In Operando Study
journal, January 2015

  • Waldmann, Thomas; Bisle, Gunther; Hogg, Björn-Ingo
  • Journal of The Electrochemical Society, Vol. 162, Issue 6
  • DOI: 10.1149/2.0561506jes

Fast charging technique for high power LiFePO4 batteries: A mechanistic analysis of aging
journal, July 2016


An accelerated calendar and cycle life study of Li-ion cells
journal, October 2001


Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries
journal, July 2018

  • Zhang, Yongzhi; Xiong, Rui; He, Hongwen
  • IEEE Transactions on Vehicular Technology, Vol. 67, Issue 7
  • DOI: 10.1109/TVT.2018.2805189

Systematic aging of commercial LiFePO 4 |Graphite cylindrical cells including a theory explaining rise of capacity during aging
journal, March 2017


Parameter Estimation and Capacity Fade Analysis of Lithium-Ion Batteries Using Reformulated Models
journal, January 2011

  • Ramadesigan, Venkatasailanathan; Chen, Kejia; Burns, Nancy A.
  • Journal of The Electrochemical Society, Vol. 158, Issue 9
  • DOI: 10.1149/1.3609926

Nonlinear aging of cylindrical lithium-ion cells linked to heterogeneous compression
journal, February 2016


Method for estimating capacity and predicting remaining useful life of lithium-ion battery
journal, August 2014


Aging of a Commercial Graphite/LiFePO4 Cell
journal, January 2011

  • Safari, M.; Delacourt, C.
  • Journal of The Electrochemical Society, Vol. 158, Issue 10
  • DOI: 10.1149/1.3614529

Characterizing aging effects of lithium ion batteries by impedance spectroscopy
journal, January 2006


Predicting and Extending the Lifetime of Li-Ion Batteries
journal, January 2013

  • Burns, J. C.; Kassam, Adil; Sinha, N. N.
  • Journal of The Electrochemical Society, Vol. 160, Issue 9
  • DOI: 10.1149/2.060309jes

Modeling of lithium plating induced aging of lithium-ion batteries: Transition from linear to nonlinear aging
journal, August 2017


Regularization and variable selection via the elastic net
journal, April 2005


Review of the Remaining Useful Life Prognostics of Vehicle Lithium-Ion Batteries Using Data-Driven Methodologies
journal, May 2016

  • Wu, Lifeng; Fu, Xiaohui; Guan, Yong
  • Applied Sciences, Vol. 6, Issue 6
  • DOI: 10.3390/app6060166

Understanding Anomalous Behavior in Coulombic Efficiency Measurements on Li-Ion Batteries
journal, December 2014

  • Gyenes, Balazs; Stevens, D. A.; Chevrier, V. L.
  • Journal of The Electrochemical Society, Vol. 162, Issue 3
  • DOI: 10.1149/2.0191503jes

Gaussian Process Regression for In Situ Capacity Estimation of Lithium-Ion Batteries
journal, January 2019

  • Richardson, Robert R.; Birkl, Christoph R.; Osborne, Michael A.
  • IEEE Transactions on Industrial Informatics, Vol. 15, Issue 1
  • DOI: 10.1109/TII.2018.2794997

Modeling and Simulation of Lithium-Ion Batteries from a Systems Engineering Perspective
journal, January 2012

  • Ramadesigan, Venkatasailanathan; Northrop, Paul W. C.; De, Sumitava
  • Journal of The Electrochemical Society, Vol. 159, Issue 3
  • DOI: 10.1149/2.018203jes

Production caused variation in capacity aging trend and correlation to initial cell performance
journal, February 2014


Comparison of prognostic algorithms for estimating remaining useful life of batteries
journal, June 2009

  • Saha, Bhaskar; Goebel, Kai; Christophersen, Jon
  • Transactions of the Institute of Measurement and Control, Vol. 31, Issue 3-4
  • DOI: 10.1177/0142331208092030

Remaining useful life prediction of lithium-ion battery with unscented particle filter technique
journal, June 2013


Electrical Energy Storage for the Grid: A Battery of Choices
journal, November 2011


Aging mechanism in Li ion cells and calendar life predictions
journal, July 2001


Synthesize battery degradation modes via a diagnostic and prognostic model
journal, December 2012


Online state of health estimation on NMC cells based on predictive analytics
journal, July 2016


Capacity fade analysis of a lithium ion cell
journal, May 2008


Degradation diagnostics for lithium ion cells
journal, February 2017


Analysis of ageing inhomogeneities in lithium-ion battery systems
journal, October 2013


Evaluation of Effects of Additives in Wound Li-Ion Cells Through High Precision Coulometry
journal, January 2011

  • Burns, J. C.; Jain, Gaurav; Smith, A. J.
  • Journal of The Electrochemical Society, Vol. 158, Issue 3
  • DOI: 10.1149/1.3531997

Lithium-Ion Battery Remaining Useful Life Prediction With Box–Cox Transformation and Monte Carlo Simulation
journal, February 2019

  • Zhang, Yongzhi; Xiong, Rui; He, Hongwen
  • IEEE Transactions on Industrial Electronics, Vol. 66, Issue 2
  • DOI: 10.1109/TIE.2018.2808918

Lithium-ion battery cell degradation resulting from realistic vehicle and vehicle-to-grid utilization
journal, April 2010


Effects of Inhomogeneities—Nanoscale to Mesoscale—on the Durability of Li-Ion Batteries
journal, February 2013

  • Harris, Stephen J.; Lu, Peng
  • The Journal of Physical Chemistry C, Vol. 117, Issue 13
  • DOI: 10.1021/jp311431z

Aging Mechanisms of LiFePO[sub 4] Batteries Deduced by Electrochemical and Structural Analyses
journal, January 2010

  • Liu, Ping; Wang, John; Hicks-Garner, Jocelyn
  • Journal of The Electrochemical Society, Vol. 157, Issue 4
  • DOI: 10.1149/1.3294790

Rapidly falling costs of battery packs for electric vehicles
journal, March 2015


Enabling fast charging – A battery technology gap assessment
journal, November 2017


Holistic computational structure screening of more than 12 000 candidates for solid lithium-ion conductor materials
journal, January 2017

  • Sendek, Austin D.; Yang, Qian; Cubuk, Ekin D.
  • Energy & Environmental Science, Vol. 10, Issue 1
  • DOI: 10.1039/C6EE02697D

Cyclable Lithium and Capacity Loss in Li-Ion Cells
journal, January 2005

  • Christensen, John; Newman, John
  • Journal of The Electrochemical Society, Vol. 152, Issue 4
  • DOI: 10.1149/1.1870752

Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO 2 Reduction
journal, August 2017


Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells
journal, February 2017


Differential voltage analyses of high-power, lithium-ion cells
journal, January 2005


Mathematical Modeling of the Lithium Deposition Overcharge Reaction in Lithium-Ion Batteries Using Carbon-Based Negative Electrodes
journal, January 1999

  • Arora, Pankaj
  • Journal of The Electrochemical Society, Vol. 146, Issue 10
  • DOI: 10.1149/1.1392512

Differential voltage analysis as a tool for analyzing inhomogeneous aging: A case study for LiFePO4|Graphite cylindrical cells
journal, November 2017


Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods
journal, October 2013


Theory of SEI Formation in Rechargeable Batteries: Capacity Fade, Accelerated Aging and Lifetime Prediction
journal, December 2012

  • Pinson, Matthew B.; Bazant, Martin Z.
  • Journal of The Electrochemical Society, Vol. 160, Issue 2
  • DOI: 10.1149/2.044302jes

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

Remaining useful life estimation – A review on the statistical data driven approaches
journal, August 2011

  • Si, Xiao-Sheng; Wang, Wenbin; Hu, Chang-Hua
  • European Journal of Operational Research, Vol. 213, Issue 1
  • DOI: 10.1016/j.ejor.2010.11.018

Symmetric cell approach and impedance spectroscopy of high power lithium-ion batteries
journal, June 2001


State-of-health monitoring of 18650 4S packs with a single-point impedance diagnostic
journal, November 2014


Nonlinear aging characteristics of lithium-ion cells under different operational conditions
journal, June 2015


Lithium-ion cell-to-cell variation during battery electric vehicle operation
journal, November 2015


Critical review of the methods for monitoring of lithium-ion batteries in electric and hybrid vehicles
journal, July 2014


High-Precision Differential Capacity Analysis of LiMn2O4/graphite Cells
journal, January 2011

  • Smith, A. J.; Burns, J. C.; Dahn, J. R.
  • Electrochemical and Solid-State Letters, Vol. 14, Issue 4
  • DOI: 10.1149/1.3543569

A Mathematical Model for the Lithium-Ion Negative Electrode Solid Electrolyte Interphase
journal, January 2004

  • Christensen, John; Newman, John
  • Journal of The Electrochemical Society, Vol. 151, Issue 11
  • DOI: 10.1149/1.1804812

High-throughput computational design of cathode coatings for Li-ion batteries
journal, December 2016

  • Aykol, Muratahan; Kim, Soo; Hegde, Vinay I.
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms13779

Machine-learning-assisted materials discovery using failed experiments
journal, May 2016

  • Raccuglia, Paul; Elbert, Katherine C.; Adler, Philip D. F.
  • Nature, Vol. 533, Issue 7601
  • DOI: 10.1038/nature17439

A general-purpose machine learning framework for predicting properties of inorganic materials
journal, August 2016


Power fade and capacity fade resulting from cycle-life testing of Advanced Technology Development Program lithium-ion batteries
journal, June 2003


Planning chemical syntheses with deep neural networks and symbolic AI
journal, March 2018

  • Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.
  • Nature, Vol. 555, Issue 7698
  • DOI: 10.1038/nature25978