Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Feature engineering for machine learning enabled early prediction of battery lifetime

Journal Article · · Journal of Power Sources
ORCiD logo [1];  [1]; ORCiD logo [1];  [1];  [1]; ORCiD logo [1]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
+ Show Author Affiliations

Accurate battery lifetime estimates enable accelerated design of novel battery materials and determination of optimal use protocols for longevity in deployments. Unfortunately, traditional battery testing may take years to reach thousands of cycles. Recent studies have shown that machine learning (ML) tools can predict lithium-ion battery lifetimes from 100 or fewer preliminary cycles, representing only a few weeks of cycling. Until now, conclusions about the efficacy and broad applicability of these predictions across a variety of cathode chemistries have been limited by available experimental information. In this work, we leverage a battery cycling dataset representing six cathode chemistries (NMC111, NMC532, NMC622, NMC811, HE5050, and 5Vspinel), multiple electrolyte/anode compositions, and 300 total carefully prepared pouch batteries to explore feature selection and battery chemistry's role in ML battery lifetime predictions. Here, a mean absolute error (MAE) of 78 cycles in prediction was seen for a chemistry-spanning test set from 100 preliminary cycles. Furthermore, an MAE of 103 cycles was seen when using only the first cycle. This study represents an in-depth investigation of strategies for feature selection for battery lifetime prediction, ML models' generalization across multiple battery chemistries, and predictions beyond the training set in the chemical space.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
1880134
Journal Information:
Journal of Power Sources, Journal Name: Journal of Power Sources Vol. 527; ISSN 0378-7753
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (26)

Understanding the Degradation Mechanisms of LiNi 0.5 Co 0.2 Mn 0.3 O 2 Cathode Material in Lithium Ion Batteries journal August 2013
Synergistic Effect of Nitrogen in Cobalt Nitride and Nitrogen-Doped Hollow Carbon Spheres for the Oxygen Reduction Reaction journal May 2015
Extremely randomized trees journal March 2006
An accelerated calendar and cycle life study of Li-ion cells journal October 2001
Cycle aging of commercial NMC/graphite pouch cells at different temperatures journal September 2015
Towards the swift prediction of the remaining useful life of lithium-ion batteries with end-to-end deep learning journal November 2020
Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells journal August 2020
Prediction of future capacity and internal resistance of Li-ion cells from one cycle of input data journal September 2021
Novel battery state-of-health online estimation method using multiple health indicators and an extreme learning machine journal October 2018
Differential voltage analyses of high-power, lithium-ion cells journal January 2005
Ageing mechanisms in lithium-ion batteries journal September 2005
Improved cycling performance of 5 V spinel LiMn1.5Ni0.5O4 by amorphous FePO4 coating journal December 2012
From coin cells to 400 mAh pouch cells: Enhancing performance of high-capacity lithium-ion cells via modifications in electrode constitution and fabrication journal August 2014
Degradation diagnostics for lithium ion cells journal February 2017
The capacity estimation and cycle life prediction of lithium-ion batteries using a new broad extreme learning machine approach journal November 2020
One-shot battery degradation trajectory prediction with deep learning journal September 2021
A machine learning framework for early detection of lithium plating combining multiple physics-based electrochemical signatures journal March 2021
Well-Ordered Transition Metal Oxide Layers in Model Catalysis – A Series of Case Studies journal December 2012
Data-driven prediction of battery cycle life before capacity degradation journal March 2019
Correlating cation ordering and voltage fade in a lithium–manganese-rich lithium-ion battery cathode oxide: a joint magnetic susceptibility and TEM study journal January 2013
Prognostics Methods for Battery Health Monitoring Using a Bayesian Framework journal February 2009
Lithium-Ion Batteries Health Prognosis Considering Aging Conditions journal July 2019
Wide Operating Temperature Range Electrolytes for High Voltage and High Specific Energy Li-Ion Cells journal April 2013
Challenging Practices of Algebraic Battery Life Models through Statistical Validation and Model Identification via Machine-Learning journal February 2021
Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis journal April 2021
Lithium Ion Battery Anode Aging Mechanisms journal March 2013

Similar Records

Related Subjects

25 ENERGY STORAGE
artificial intelligence
battery
feature engineering
life prediction
lifetime prediction
lithium-ion
lithium-ion battery
machine learning
state of health