Related Experiment Video
Updated: Jun 16, 2025
10:03
Characterization of Electrode Materials for Lithium Ion and Sodium Ion Batteries Using Synchrotron Radiation Techniques
Published on: November 11, 2013
25.4K
Analysis of Lithium Aging Using Machine Learning-Enhanced Spectroscopy Techniques
James T Stofel1, Ashwin P Rao2, Anil K Patnaik1
1Department of Engineering Physics, Air Force Institute of Technology, Wright-Patterson AFB, Ohio, USA.
Applied Spectroscopy
|August 21, 2024
Summary
This study uses laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy with machine learning to identify lithium compounds. The methods accurately classify lithium hydride, hydroxide, and carbonate, and quantify compound ingrowth.
Area of Science:
- Analytical Chemistry
- Materials Science
Background:
- Lithium compounds like LiH and LiOH are industrially important but reactive.
- Reactions with H2O and CO2 lead to secondary compound ingrowth, affecting material homogeneity and applications.
Purpose of the Study:
- To develop and validate spectroscopic methods for analyzing lithium compound mixtures.
- To quantitatively assess the ingrowth of lithium hydroxide (LiOH) in lithium hydride (LiH).
Main Methods:
- Utilized laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy for spectral data acquisition.
- Employed machine learning, including support vector machine (SVM) classifiers, for high-fidelity classification of LiH, LiOH, and Li2CO3.
- Applied multivariate regression techniques, specifically partial least-squares regression (PLSR), for quantitative analysis.
Main Results:
- Achieved perfect prediction accuracy in classifying LiH, LiOH, and Li2CO3 using SVM classifiers.
- Developed a data fusion model combining LIBS and Raman features using PLSR.
- The optimized model demonstrated a root mean square error of 2.5 wt% and a detection limit of 6.3 wt% for LiOH ingrowth in LiH.
Conclusions:
- LIBS and Raman spectroscopy, coupled with machine learning, provide a robust approach for analyzing lithium compound mixtures.
- The developed methods enable accurate classification and quantification of secondary lithium compound formation.
- This technique is crucial for ensuring the quality and performance of lithium chemicals in industrial applications.
