Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A hybrid CNN-DNN model for battery remaining useful life RUL prediction.

Hala Khoufi¹, Emna Bouazizi², Ayman E Khedr²

¹College of Computing and Information Technology at Khulais, Department of Information Systems, University of Jeddah, Jeddah, 21959, Saudi Arabia. hnageb@uj.edu.sa.

Scientific Reports

|June 1, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Air quality prediction via hybrid BiGRU-MLP using binary ant colony optimization and firefly algorithm for hyperparameter tuning.

Scientific reports·2026

Same author

Rapid earthquake damage assessment via hybrid LSTM-RNN with a quantum-inspired classification head based on Autonomous Perceptron Model APM.

Scientific reports·2026

Same author

A hybrid LSTM-GRU framework for lung cancer classification using GWO-WOA algorithm for hyperparameter tuning and BPSO for feature selection.

Scientific reports·2026

Same author

SD-MAC protocol for wireless sensor network energy consumption.

Scientific reports·2026

Same author

CNN-MLP framework for forest burned areas prediction using PSO-WOA algorithm.

Scientific reports·2026

Same author

Enhancing encrypted HTTPS traffic classification based on stacked deep ensembles models.

Scientific reports·2025

Accurate prediction of lithium-ion battery Remaining Useful Life (RUL) is crucial. This study introduces an optimized hybrid deep learning framework using Convolutional Neural Networks and Deep Neural Networks for superior RUL prediction, enhancing battery management systems.

Area of Science:

* Electrical Engineering and Computer Science, focusing on artificial intelligence and machine learning applications in energy storage.

Background:

* Reliable Remaining Useful Life (RUL) prediction for lithium-ion batteries is critical for safety, reliability, and maintenance in energy storage systems.
* Existing methods often struggle with the complexity and nonlinearity of battery degradation data.

Purpose of the Study:

* To develop and validate an optimized hybrid deep learning framework for accurate lithium-ion battery RUL prediction.
* To enhance feature extraction and selection for improved predictive performance.

Main Methods:

* Integration of Convolutional Neural Networks (CNNs) for automatic feature extraction and Deep Neural Networks (DNNs) for nonlinear relationship modeling.
* Application of Binary Particle Swarm Optimization (BPSO) for optimal feature selection to reduce redundancy and improve accuracy.

Keywords:

Binary Particle Swarm Optimization (BPSO)Deep learning prognostics Hybrid CNN-DNN Remaining Lithium-ion battery Remaining Useful Life (RUL)Wrapper feature selection

Related Experiment Videos

* Utilized a publicly available dataset of 680 lithium-ion battery degradation samples, divided into 70% training, 15% validation, and 15% testing sets.

Main Results:

* The proposed hybrid model achieved a coefficient of determination of 99.01%.
* Achieved superior performance with a Mean Squared Error (MSE) of 0.0141 and Mean Absolute Error (MAE) of 0.0931.
* Demonstrated significant outperformance compared to other deep learning models in RUL prediction.

Conclusions:

* The optimized hybrid deep learning framework offers a robust and accurate solution for lithium-ion battery RUL prediction.
* The framework shows strong potential for deployment in intelligent battery management systems for enhanced operational efficiency and safety.