AE-BPNN: autoencoder and backpropagation neural network-based model for lithium-ion battery state of health estimation
Bibliographic record
Abstract
Lithium-ion (Li-ion) batteries play a crucial role in modern energy storage systems, with their performance and longevity heavily dependent on accurately assessing their State of Health (SOH). Electrochemical Impedance Spectroscopy (EIS) has emerged as a powerful technique for SOH evaluation, capturing the battery's intricate electrochemical properties. However, practical EIS implementation poses challenges due to the need for expensive equipment and controlled testing conditions. This study introduces a data-driven approach to estimate the SOH of Li-ion batteries using EIS data. An autoencoder backpropagation neural network (AE-BPNN) was developed for unsupervised processing, dimensionality reduction, feature extraction, and SOH estimation. Two optimization algorithms-Scaled Conjugate Gradient (SCG) and Resilient Backpropagation (RBP)-were utilized to tune network weights and enhance performance. Experiments were conducted on eight Eunicell cells across six operational states (I, II, III, IV, V, IX) at various temperatures (25 °C, 35 °C, 45 °C). The AE-BPNN model demonstrated significant advantages over Gaussian Process Regression (GPR) and Support Vector Regression (SVR), yielding lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), alongside higher R² scores. Across all evaluated states, the AE-BPNN achieved the lowest average RMSE values of 0.0192 and 0.0176 for the 35C02 and 45C02 cells, respectively, compared to GPR (0.0429, 0.0485) and SVR (0.0404, 0.0334), thereby confirming its superior accuracy in estimating the state of health of Li-ion batteries.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".