User-Friendly Freeware for Determining the Concentration of Electrolyte Components in Lithium-Ion Cells Using Fourier Transform Infrared Spectroscopy, Beer's Law, and Machine Learning
Bibliographic record
Abstract
Understanding the changes in the electrolyte during lithium-ion cell aging is valuable in order to improve longevity. Studying this in hundreds or thousands of cells requires a fast and widely available measurement such as Fourier Transform Infrared Spectroscopy (FTIR) of electrolyte samples. This article expands on a previous work to use a new model more grounded in the physics of the measurement and machine learning to determine electrolyte composition from FTIR measurements. A carefully prepared dataset of mixtures of 5 electrolyte components (i.e. LiPF 6 , EC, EMC, DMC, and DEC), and the code to replicate and extend the model to different electrolyte mixtures are made available. With this new model, the mass ratio of salt to total is predicted within an error of 0.4%, and each solvent's mass ratio to total is predicted within an error of 2%. Furthermore, a calculated spectrum based on the predicted components can be compared to the measurement which allows one to detect if unexpected species are present in the electrolyte in significant quantity. A model for mixtures of 5 components can be calibrated well with between 25 and 50 carefully prepared samples so this work can be extended to other systems by simply adding more data and retraining.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.192 | 0.099 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".