Method and system for determining concentration of electrolyte components for lithium-ion cells
A computer-implemented method for determining a concentration of a component of an electrolyte in a lithium-ion or for a lithium-ion cell is provided. The method includes providing, to a spectrometer, instructions to capture a spectrum of a sample solution of the electrolyte and generate a signal. The method includes analyzing the signal to determine one or more spectral features of the spectrum. The method includes preparing a database of spectra corresponding to solutions having predetermined concentrations of the component of the electrolyte wherein the database includes a plurality for spectral features for each solution. The method further includes determining a machine learning (ML) model using the database of spectra. The method includes determining the concentration of the component of the electrolyte in the sample solution using the machine learning model.
1. A computer-implemented method for determining a concentration of a component of an electrolyte, the computer-implemented method comprising:
providing, to a spectrometer, instructions to capture a spectrum of a sample solution of the electrolyte and generate a signal representing the spectrum;
receiving, from the spectrometer, the signal;
analyzing the signal to determine one or more spectral features of the spectrum;
preparing a database of spectra corresponding to solutions having predetermined concentrations of the component of the electrolyte, the database comprising a plurality for spectral features for each solution;
determining a machine learning model using the database of spectra, the machine learning model based on at least one of the plurality of spectral features and the concentration of the component of the electrolyte; and
determining the concentration of the component of the electrolyte in the sample solution using the machine learning model, wherein the component of the electrolyte is LiPF 6 .
2. The computer-implemented method of claim 1 , wherein the spectrometer is one of an infrared spectrometer, a Raman spectrometer, and an ultraviolet visible (UV-Vis) spectrometer.
3. The computer-implemented method of claim 2 , wherein the spectrometer is a Fourier transform infrared (FTIR) spectrometer.
4. The computer-implemented method of claim 3 , wherein providing instructions comprises providing instructions to the spectrometer to perform attenuated total reflectance (ATR) Fourier Transform infrared spectroscopy on the sample solution.
5. The computer-implemented method of claim 3 , wherein providing instructions comprises providing instructions to the infrared spectrometer to capture the infrared spectrum of the sample solution using infrared radiation having a wavenumber between 500 cm −1 to 1500 cm −1 .
6. The computer-implemented method of claim 3 , wherein analyzing the signal to determine the one or more spectral features of the infrared spectrum comprises determining an area of the signal in a first set of predetermined regions.
7. The computer-implemented method of claim 3 , wherein analyzing the signal to determine one or more spectral features of the infrared spectrum comprises determining a wavenumber of the signal in a second set of predetermined regions.
8. The computer-implemented method of claim 3 , wherein determining the machine learning model comprises fitting the variation of each of the plurality of spectral features with the corresponding predetermined concentrations of the component of the electrolyte on a surface using least squares fitting technique.
9. The computer-implemented method of claim 8 , wherein determining the concentration of the component of the electrolyte comprises fitting the one or more spectral features to the corresponding surface determined by the machine learning model.
10. A system for determining a concentration of a component of an electrolyte in a lithium-ion cell, the system comprising:
a spectrometer configured to:
subject a sample solution of the electrolyte to radiation;
capture a spectrum of the sample solution of the electrolyte; and
produce a signal representing the spectrum; and
a processor in electrical communication with the spectrometer, the processor configured to:
analyze the signal to determine one or more spectral features of the spectrum;
prepare a database of spectra corresponding to solutions having predetermined concentrations of the component of the electrolyte, the database comprising a plurality for spectral features for each solution;
determine a machine learning model using the database of spectra, the machine learning model based on at least one of the plurality of spectral features and the concentration of the component of the electrolyte; and
determine the concentration of the component of the electrolyte in the sample solution using the machine learning model, wherein the component of the electrolyte is LiPF 6 .
11. The system of claim 10 , wherein the spectrometer is one of an infrared spectrometer, a Raman spectrometer, and an ultraviolet visible (UV-Vis) spectrometer.
12. The system of claim 11 , wherein the spectrometer is a Fourier transform infrared (FTIR) spectrometer.
13. The system of claim 12 , wherein the spectrometer is configured to subject the sample solution to infrared radiation having a wavenumber between 500 cm −1 to 1500 cm −1 .
14. The system of claim 12 , wherein the processor is configured to analyze the signal to determine the one or more spectral features of the infrared spectrum by determining an area of the signal in a first set of predetermined regions.
15. The system of claim 12 , wherein the processor is configured to analyze the signal to determine the one or more spectral features of the infrared spectrum by determining a wavenumber of the signal in a second set of predetermined regions.
16. The system of claim 12 , wherein the processor is configured to determine the machine learning model by fitting the variation of each of the plurality of spectral features with the corresponding predetermined concentrations of the component of the electrolyte on a surface using least squares fitting technique.
17. The system of claim 16 , wherein the processor is configured to determine the concentration of the component of the electrolyte by fitting the one or more spectral features to the corresponding surface determined by the machine learning model.
18. The system of claim 17 , wherein the processor is configured to determine the concentration of the component of the electrolyte by fitting the one or more spectral features using least squares fitting technique.
19. A computer-readable medium for use in conjunction with a spectrometer to determine a concentration of a component of an electrolyte, the computer-program product comprising a non-transitory computer-readable storage medium having instructions for causing a processor to:
provide, to the spectrometer, instructions to capture a spectrum of a sample solution of the electrolyte and generate a signal;
receive, from the spectrometer, the signal;
analyze the signal to determine one or more spectral features of the spectrum;
prepare a database of spectra corresponding to solutions having predetermined concentrations of the component of the electrolyte, the database comprising a plurality for spectral features for each solution;
determine a machine learning model using the database of spectra, the machine learning model based on at least one of the plurality of spectral features and the concentration of the component of the electrolyte; and
determine the concentration of the component of the electrolyte in the sample solution using the machine learning model, wherein the component of the electrolyte is LiPF 6 .