Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra

Journal Article · · Journal of the Electrochemical Society
 [1];  [2];  [3];  [4];  [5];  [6];  [7];  [8];  [2];  [9];  [10];  [11];  [12]
  1. Technical Univ. of Darmstadt (Germany); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  2. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
  3. Titan Advanced Energy Solutions, Salem, MA (United States)
  4. Kingston, MA (United States)
  5. Univ. of Oxford (United Kingdom)
  6. Universidad Pontificia Bolivariana, Medellin (Colombia)
  7. Verasonics SAS, Medellin (Colombia)
  8. Carnegie Mellon Univ., Pittsburgh, PA (United States)
  9. Chemix.ai, Sunnyvale, CA (United States)
  10. Technical Univ. of Darmstadt (Germany)
  11. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  12. Battery Associates, Dublin (Ireland)
+ Show Author Affiliations

Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various resistance, capacitive, inductive, or diffusion responses. For small data sets, this procedure can be conducted manually; however, it is not feasible to manually define a proper ECM for extensive data sets with a wide range of EIS responses. Automatic identification of an ECM would substantially accelerate the analysis of large sets of EIS data. We showcase machine learning methods to classify the ECMs of 9,300 impedance spectra provided by QuantumScape for the BatteryDEV hackathon. The best-performing approach is a gradient-boosted tree model utilizing a library to automatically generate features, followed by a random forest model using the raw spectral data. A convolutional neural network using boolean images of Nyquist representations is presented as an alternative, although it achieves a lower accuracy. We publish the data and open source the associated code. The approaches described in this article can serve as benchmarks for further studies. A key remaining challenge is the identifiability of the labels, underlined by the model performances and the comparison of misclassified spectra.

Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office
Grant/Contract Number:
AC36-08GO28308
OSTI ID:
1992511
Report Number(s):
NREL/JA-5700-86260; MainId:87033; UUID:54988a46-cff7-4cac-83c3-8de754a7fc55; MainAdminID:70028
Journal Information:
Journal of the Electrochemical Society, Journal Name: Journal of the Electrochemical Society Journal Issue: 6 Vol. 170; ISSN 0013-4651
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (42)

Panasonic 18650PF Li-ion Battery Data dataset January 2018
UofM Pouch Cell Voltage and Expansion Cyclic Aging Dataset dataset January 2021
Analysis of Lithium-Ion Battery Models Based on Electrochemical Impedance Spectroscopy journal August 2016
Electrochemical impedance spectroscopy as a tool for investigating underpaint corrosion journal May 1996
Impedance study of (PEO)10LiClO4–Al2O3 composite polymer electrolyte with blocking electrodes journal March 2001
A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea journal November 2019
Latent Variable Method Demonstrator — software for understanding multivariate data analytics algorithms journal November 2022
Exploring the use of machine learning for interpreting electrochemical impedance spectroscopy data: evaluation of the training dataset size journal April 2022
Towards robust autonomous impedance spectroscopy analysis: A calibrated hierarchical Bayesian approach for electrochemical impedance spectroscopy (EIS) inversion journal January 2021
EIS equivalent circuit model prediction using interpretable machine learning and parameter identification using global optimization algorithms journal June 2022
Investigation of the low frequency Warburg impedance of Li-ion cells by frequency domain measurements journal February 2019
Equivalent circuit model recognition of electrochemical impedance spectroscopy via machine learning journal December 2019
Integration of an XGBoost model and EIS detection to determine the effect of low inhibitor concentrations on E. coli journal November 2020
Predicting battery end of life from solar off-grid system field data using machine learning journal December 2021
Principles of the Battery Data Genome journal October 2022
Characterization of high-power lithium-ion batteries by electrochemical impedance spectroscopy. I. Experimental investigation journal June 2011
Study of proton exchange membrane fuel cells using electrochemical impedance spectroscopy technique – A review journal October 2013
Determination of suitable parameters for battery analysis by Electrochemical Impedance Spectroscopy journal August 2017
Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh – A Python package) journal September 2018
Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering journal March 2020
Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning journal April 2020
Impedance-based forecasting of lithium-ion battery performance amid uneven usage journal August 2022
Crowd-sourcing materials-science challenges with the NOMAD 2018 Kaggle competition journal November 2019
Data-driven prediction of battery cycle life before capacity degradation journal March 2019
Closed-loop optimization of fast-charging protocols for batteries with machine learning journal February 2020
Symmetry prediction and knowledge discovery from X-ray diffraction patterns using an interpretable machine learning approach journal December 2020
Electrochemical impedance spectroscopy journal June 2021
A high performance supercapacitor based on a ceria/graphene nanocomposite synthesized by a facile sonochemical method journal January 2015
Towards development of a novel universal medical diagnostic method: Raman spectroscopy and machine learning journal January 2020
Machine learning and chemometrics for electrochemical sensors: moving forward to the future of analytical chemistry journal January 2021
Electrochemical impedance spectroscopy: an overview of bioanalytical applications journal January 2013
The statistics of natural images journal January 1994
XGBoost: A Scalable Tree Boosting System conference January 2016
Reversible and Irreversible Expansion of Lithium-Ion Batteries Under a Wide Range of Stress Factors journal October 2021
Theoretical and Experimental Analysis of Porous Electrodes for Lithium-Ion Batteries by Electrochemical Impedance Spectroscopy Using a Symmetric Cell journal January 2012
Exploring Impedance Growth in High Voltage NMC/Graphite Li-Ion Cells Using a Transmission Line Model journal December 2015
Analysis of Li-Ion Battery Electrochemical Impedance Spectroscopy Data: An Easy-to-Implement Approach for Physics-Based Parameter Estimation Using an Open-Source Tool journal January 2018
Analysis of Thousands of Electrochemical Impedance Spectra of Lithium-Ion Cells through a Machine Learning Inverse Model journal January 2019
Review—Dynamic Models of Li-Ion Batteries for Diagnosis and Operation: A Review and Perspective journal January 2018
A rapid neural network–based state of health estimation scheme for screening of end of life electric vehicle batteries
  • Rastegarpanah, Alireza; Hathaway, Jamie; Ahmeid, Mohamed
  • Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, Vol. 235, Issue 3 https://doi.org/10.1177/0959651820953254
journal September 2020
Modeling and Applications of Electrochemical Impedance Spectroscopy (EIS) for Lithium-ion Batteries journal February 2020
Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning dataset January 2020

Figures / Tables (13)

Table I(p. 2)table Table I
Table II(p. 2)table Table II
Figure 1(p. 3)figure Figure 1
Figure 2(p. 4)figure Figure 2
Table III(p. 6)table Table III
Figure 3(p. 7)figure Figure 3
Figure 4(p. 7)figure Figure 4
Figure 5(p. 8)figure Figure 5
Figure 6(p. 8)figure Figure 6
Figure 7(p. 9)figure Figure 7
Figure 8(p. 9)figure Figure 8
Figure 9(p. 10)figure Figure 9
Table IV(p. 10)table Table IV

Similar Records

Parasitic Effects in Impedance Spectrum of PEM Water Electrolysis Cells: Case Study of High-Frequency Inductive Effects
Journal Article · Fri Jun 02 00:00:00 EDT 2023 · Energy Technology · OSTI ID:1992308
A mathematical approach to survey electrochemical impedance spectroscopy for aging in lithium-ion batteries
Journal Article · Mon Feb 27 23:00:00 EST 2023 · Frontiers in Energy Research · OSTI ID:1960083
The deep-DRT: A deep neural network approach to deconvolve the distribution of relaxation times from multidimensional electrochemical impedance spectroscopy data
Journal Article · Sat Jul 31 00:00:00 EDT 2021 · Electrochimica Acta · OSTI ID:1831633

Related Subjects

25 ENERGY STORAGE
30 DIRECT ENERGY CONVERSION
classification
electrochemical impedance spectroscopy
equivalent circuit model
hackathon
lithium-ion batteries
machine learning
open data