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

Accurate prediction of the Remaining Useful Life of lithium-ion batteries is essential for enhancing reliability, safety, and maintenance planning in energy storage systems. This study proposes an optimized hybrid deep learning framework that integrates Convolutional Neural Networks with Deep Neural Networks for effective battery remaining useful life prediction. The model leverages convolutional neural network layers to automatically extract discriminative features from multivariate battery degradation data, while deep neural network layers model complex nonlinear relationships for precise regression estimation. To further enhance predictive performance and reduce feature redundancy, Binary Particle Swarm Optimization is employed for optimal feature selection. Experiments were conducted using a publicly available lithium-ion battery degradation dataset comprising 680 samples with electrical, thermal, and health-related parameters, including State of Health and remaining useful life indicators. The dataset was divided into training, validation, and testing subsets with proportions of 70%, 15%, and 15%, respectively. A comprehensive performance evaluation was performed using Mean Squared Error, Mean Absolute Percentage Error, Median Absolute Error, Mean Absolute Error, and the coefficient of determination. The proposed hybrid model achieved superior performance with a Mean Squared Error of 0.0141, Mean Absolute Error of 0.0931, Mean Absolute Percentage Error of 0.0142, Median Absolute Error of 0.0739, and a coefficient of determination of 99.01%, significantly outperforming comparative deep learning models. These results demonstrate that the proposed framework provides a robust and accurate solution for lithium-ion battery remaining useful life prediction and supports its potential deployment in intelligent battery management systems.