What question did this study set out to answer?

The study aims to improve the prediction of lithium-ion battery state of health (SOH) using a hybrid model that combines several advanced techniques.

June 10, 2026BatteriesOpen Access

Lithium-Ion Battery State of Health Prediction Using a Hybrid BiLSTM–Random Forest Framework

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved state of health prediction in lithium-ion batteries, indicating enhanced monitoring capabilities.

The study aims to improve the prediction of lithium-ion battery state of health (SOH) using a hybrid model that combines several advanced techniques.
Developed a hybrid BiLSTM-Random Forest model integrating wavelet denoising and PCA-based feature compression.
Utilized NASA battery datasets and the Oxford Battery Degradation Dataset for model testing and validation.
Applied leave-one-battery-out cross-validation for robust performance evaluation.
Achieved a minimum RMSE value of 0.0229 for NASA battery B0007 and 0.0024 for Oxford Cell3.
Demonstrated superior performance compared to benchmark models (CNN-LSTM, BiLSTM, RF) in prediction accuracy.
Ablation analysis confirmed that the combination of various techniques significantly enhanced SOH estimation performance.

Mohamud et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark