DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Closed-loop optimization of fast-charging protocols for batteries with machine learning

Abstract

Simultaneously optimizing many design parameters in time-consuming experiments causes bottlenecks in a broad range of scientific and engineering disciplines. One such example is process and control optimization for lithium-ion batteries during materials selection, cell manufacturing and operation. A typical objective is to maximize battery lifetime; however, conducting even a single experiment to evaluate lifetime can take months to years. Furthermore, both large parameter spaces and high sampling variability necessitate a large number of experiments. As such, the key challenge is to reduce both the number and the duration of the experiments required. Here we develop and demonstrate a machine learning methodology to efficiently optimize a parameter space specifying the current and voltage profiles of six-step, ten-minute fast-charging protocols for maximizing battery cycle life, which can alleviate range anxiety for electric-vehicle users. We combine two key elements to reduce the optimization cost: an early-prediction model, which reduces the time per experiment by predicting the final cycle life using data from the first few cycles, and a Bayesian optimization algorithm, which reduces the number of experiments by balancing exploration and exploitation to efficiently probe the parameter space of charging protocols. Using this methodology, we rapidly identify high-cycle-life charging protocols among 224 candidatesmore » in 16 days (compared with over 500 days using exhaustive search without early prediction), and subsequently validate the accuracy and efficiency of our optimization approach. Our closed-loop methodology automatically incorporates feedback from past experiments to inform future decisions and can be generalized to other applications in battery design and, more broadly, other scientific domains that involve time-intensive experiments and multi-dimensional design spaces.« less

Authors:
 [1];  [1];  [1];  [2];  [1];  [1];  [1];  [1];  [1];  [1];  [3];  [3];  [4];  [2];  [1];  [5]
  1. Stanford Univ., CA (United States)
  2. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  3. Toyota Research Inst., Los Altos, CA (United States)
  4. Stanford Univ., CA (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  5. Stanford Univ., CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES); Toyota Research Institute; National Science Foundation (NSF); Microsoft; USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office
OSTI Identifier:
1647088
Grant/Contract Number:  
AC02-76SF00515; DGE-114747; ECCS-1542152
Resource Type:
Accepted Manuscript
Journal Name:
Nature (London)
Additional Journal Information:
Journal Name: Nature (London); Journal Volume: 578; Journal Issue: 7795; Journal ID: ISSN 0028-0836
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
25 ENERGY STORAGE; Batteries; Computer science; Statistics

Citation Formats

Attia, Peter M., Grover, Aditya, Jin, Norman, Severson, Kristen A., Markov, Todor M., Liao, Yang-Hung, Chen, Michael H., Cheong, Bryan, Perkins, Nicholas, Yang, Zi, Herring, Patrick K., Aykol, Muratahan, Harris, Stephen J., Braatz, Richard D., Ermon, Stefano, and Chueh, William C. Closed-loop optimization of fast-charging protocols for batteries with machine learning. United States: N. p., 2020. Web. doi:10.1038/s41586-020-1994-5.
Attia, Peter M., Grover, Aditya, Jin, Norman, Severson, Kristen A., Markov, Todor M., Liao, Yang-Hung, Chen, Michael H., Cheong, Bryan, Perkins, Nicholas, Yang, Zi, Herring, Patrick K., Aykol, Muratahan, Harris, Stephen J., Braatz, Richard D., Ermon, Stefano, & Chueh, William C. Closed-loop optimization of fast-charging protocols for batteries with machine learning. United States. https://doi.org/10.1038/s41586-020-1994-5
Attia, Peter M., Grover, Aditya, Jin, Norman, Severson, Kristen A., Markov, Todor M., Liao, Yang-Hung, Chen, Michael H., Cheong, Bryan, Perkins, Nicholas, Yang, Zi, Herring, Patrick K., Aykol, Muratahan, Harris, Stephen J., Braatz, Richard D., Ermon, Stefano, and Chueh, William C. Wed . "Closed-loop optimization of fast-charging protocols for batteries with machine learning". United States. https://doi.org/10.1038/s41586-020-1994-5. https://www.osti.gov/servlets/purl/1647088.
@article{osti_1647088,
title = {Closed-loop optimization of fast-charging protocols for batteries with machine learning},
author = {Attia, Peter M. and Grover, Aditya and Jin, Norman and Severson, Kristen A. and Markov, Todor M. and Liao, Yang-Hung and Chen, Michael H. and Cheong, Bryan and Perkins, Nicholas and Yang, Zi and Herring, Patrick K. and Aykol, Muratahan and Harris, Stephen J. and Braatz, Richard D. and Ermon, Stefano and Chueh, William C.},
abstractNote = {Simultaneously optimizing many design parameters in time-consuming experiments causes bottlenecks in a broad range of scientific and engineering disciplines. One such example is process and control optimization for lithium-ion batteries during materials selection, cell manufacturing and operation. A typical objective is to maximize battery lifetime; however, conducting even a single experiment to evaluate lifetime can take months to years. Furthermore, both large parameter spaces and high sampling variability necessitate a large number of experiments. As such, the key challenge is to reduce both the number and the duration of the experiments required. Here we develop and demonstrate a machine learning methodology to efficiently optimize a parameter space specifying the current and voltage profiles of six-step, ten-minute fast-charging protocols for maximizing battery cycle life, which can alleviate range anxiety for electric-vehicle users. We combine two key elements to reduce the optimization cost: an early-prediction model, which reduces the time per experiment by predicting the final cycle life using data from the first few cycles, and a Bayesian optimization algorithm, which reduces the number of experiments by balancing exploration and exploitation to efficiently probe the parameter space of charging protocols. Using this methodology, we rapidly identify high-cycle-life charging protocols among 224 candidates in 16 days (compared with over 500 days using exhaustive search without early prediction), and subsequently validate the accuracy and efficiency of our optimization approach. Our closed-loop methodology automatically incorporates feedback from past experiments to inform future decisions and can be generalized to other applications in battery design and, more broadly, other scientific domains that involve time-intensive experiments and multi-dimensional design spaces.},
doi = {10.1038/s41586-020-1994-5},
journal = {Nature (London)},
number = 7795,
volume = 578,
place = {United States},
year = {Wed Feb 19 00:00:00 EST 2020},
month = {Wed Feb 19 00:00:00 EST 2020}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 257 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Data-driven prediction of battery cycle life before capacity degradation
journal, March 2019


High-Dimensional Materials and Process Optimization Using Data-Driven Experimental Design with Well-Calibrated Uncertainty Estimates
journal, July 2017

  • Ling, Julia; Hutchinson, Maxwell; Antono, Erin
  • Integrating Materials and Manufacturing Innovation, Vol. 6, Issue 3
  • DOI: 10.1007/s40192-017-0098-z

Boostcharging Li-ion batteries: A challenging new charging concept
journal, July 2005


Accelerating the discovery of materials for clean energy in the era of smart automation
journal, April 2018

  • Tabor, Daniel P.; Roch, Loïc M.; Saikin, Semion K.
  • Nature Reviews Materials, Vol. 3, Issue 5
  • DOI: 10.1038/s41578-018-0005-z

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


Search for an Optimal Five-Step Charging Pattern for Li-Ion Batteries Using Consecutive Orthogonal Arrays
journal, June 2011

  • Liu, Yi-Hwa; Hsieh, Ching-Hsing; Luo, Yi-Feng
  • IEEE Transactions on Energy Conversion, Vol. 26, Issue 2
  • DOI: 10.1109/TEC.2010.2103077

Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


Controlling an organic synthesis robot with machine learning to search for new reactivity
journal, July 2018


Search for an optimal multistage charging pattern for lithium-ion batteries using the Taguchi approach
conference, November 2009


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


Less is more: Sampling chemical space with active learning
journal, June 2018

  • Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5023802

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


Measurement of anisotropic thermophysical properties of cylindrical Li-ion cells
journal, April 2014


Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning
journal, April 2018

  • Balachandran, Prasanna V.; Kowalski, Benjamin; Sehirlioglu, Alp
  • Nature Communications, Vol. 9, Issue 1
  • DOI: 10.1038/s41467-018-03821-9

Reconfigurable system for automated optimization of diverse chemical reactions
journal, September 2018


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


Optimal Experimental Design for Parameterization of an Electrochemical Lithium-Ion Battery Model
journal, January 2018

  • Park, Saehong; Kato, Dylan; Gima, Zach
  • Journal of The Electrochemical Society, Vol. 165, Issue 7
  • DOI: 10.1149/2.0421807jes

A High Precision Coulometry Study of the SEI Growth in Li/Graphite Cells
journal, January 2011

  • Smith, A. J.; Burns, J. C.; Zhao, Xuemei
  • Journal of The Electrochemical Society, Vol. 158, Issue 5
  • DOI: 10.1149/1.3557892

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


The Automation of Science
journal, April 2009


Automating drug discovery
journal, December 2017


Autonomy in materials research: a case study in carbon nanotube growth
journal, October 2016


Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
journal, May 2012

  • Srinivas, Niranjan; Krause, Andreas; Kakade, Sham M.
  • IEEE Transactions on Information Theory, Vol. 58, Issue 5
  • DOI: 10.1109/TIT.2011.2182033

Challenges and opportunities towards fast-charging battery materials
journal, June 2019


The effect of the charging protocol on the cycle life of a Li-ion battery
journal, October 2006


Machine learning for molecular and materials science
journal, July 2018


Calendar Aging of Lithium-Ion Batteries: I. Impact of the Graphite Anode on Capacity Fade
journal, January 2016

  • Keil, Peter; Schuster, Simon F.; Wilhelm, Jörn
  • Journal of The Electrochemical Society, Vol. 163, Issue 9
  • DOI: 10.1149/2.0411609jes

Prospects for reducing the processing cost of lithium ion batteries
journal, February 2015


Works referencing / citing this record:

Nanoporous LiNi1/3Co1/3Mn1/3O2 as an ultra-fast charge cathode material for aqueous rechargeable lithium batteries
journal, January 2013

  • Wang, Faxing; Xiao, Shiying; Chang, Zheng
  • Chemical Communications, Vol. 49, Issue 80
  • DOI: 10.1039/c3cc44360d

Multi-stage constant-current charging protocol for a high-energy-density pouch cell based on a 622NCM/graphite system
journal, January 2019

  • An, Fuqiang; Zhang, Rui; Wei, Zhiguo
  • RSC Advances, Vol. 9, Issue 37
  • DOI: 10.1039/c9ra03629f

A brief review on key technologies in the battery management system of electric vehicles
journal, April 2018


Optimal charging strategy design for lithium‐ion batteries considering minimization of temperature rise and energy loss
journal, May 2019

  • Chen, Zheng; Shu, Xing; Xiao, Renxin
  • International Journal of Energy Research, Vol. 43, Issue 9
  • DOI: 10.1002/er.4560

Modeling the Effect of Fast Charge Scenario on the Cycle Life of a Lithium-Ion Battery
journal, January 2018

  • Koo, Boram; Yi, Jaeshin; Lee, Dongcheul
  • Journal of The Electrochemical Society, Vol. 165, Issue 16
  • DOI: 10.1149/2.0281816jes

Fast computational framework for optimal life management of lithium ion batteries
journal, January 2018

  • Mandli, Aravinda R.; Ramachandran, Sanoop; Khandelwal, Ashish
  • International Journal of Energy Research, Vol. 42, Issue 5
  • DOI: 10.1002/er.3996

Numerical Analysis of the Cooling Performance in a 7.2 kW Integrated Bidirectional OBC/LDC Module
journal, December 2019

  • Noh, Jung-Hun; Song, Seong-il; Hur, Deog-Jae
  • Applied Sciences, Vol. 10, Issue 1
  • DOI: 10.3390/app10010270

Real-Time Prediction of Anode Potential in Li-Ion Batteries Using Long Short-Term Neural Networks for Lithium Plating Prevention
journal, January 2019


Determining Accelerated Charging Procedure from Half Cell Characterization
journal, January 2019

  • Yourey, William; Fu, Yanbao; Li, Ning
  • Journal of The Electrochemical Society, Vol. 166, Issue 8
  • DOI: 10.1149/2.0591908jes

Analysis of the effect of resistance increase on the capacity fade of lithium ion batteries
journal, March 2019

  • Mandli, Aravinda R.; Kaushik, Anshul; Patil, Rajkumar S.
  • International Journal of Energy Research, Vol. 43, Issue 6
  • DOI: 10.1002/er.4397

Fast Charging Lithium Batteries: Recent Progress and Future Prospects
journal, March 2019


A framework for charging strategy optimization using a physics-based battery model
journal, June 2019


An optimal multistage charge strategy for commercial lithium ion batteries
journal, January 2018

  • Liu, Jialong; Duan, Qiangling; Chen, Haodong
  • Sustainable Energy & Fuels, Vol. 2, Issue 8
  • DOI: 10.1039/c8se00235e