# Multiview state-of-health estimation for lithium-ion batteries using time–frequency image fusion and attention-based deep learning

## TL;DR

This paper introduces a new method for predicting the health of lithium-ion batteries using deep learning and time–frequency image analysis to improve accuracy.

## Contribution

The novel multiview approach combines time–frequency image fusion and attention-based deep learning for SOH estimation.

## Key findings

- Time–frequency images improve SOH prediction accuracy compared to baseline models.
- The attention mechanism enhances the capture of temporal and spatial correlations.
- Weighted integration of CNN and LSTM outputs boosts overall performance.

## Abstract

Lithium-ion batteries are high-performance energy storage devices that have been widely used in a variety of applications. Accurate early-stage prediction of their remaining useful life is essential for preventing failures and mitigating safety risks. This study proposes a novel multiview approach for estimating the State-of-Health (SOH) of lithium-ion batteries by integrating time-domain and time–frequency features. Firstly, time-domain signals are transformed into time–frequency images using a wavelet transform. Three representative features are then selected and converted into grayscale images, which are combined into three-channel color images as inputs for a convolutional neural network (CNN) to extract spatial features. These features are subsequently passed into a long short-term memory (LSTM) network to capture spatial dependencies. In parallel, raw temporal features are processed through a two-stage attention mechanism to explore both temporal and spatial correlations, followed by another LSTM to model temporal dependencies. The outputs from the two branches are fused using weighted integration and passed through a fully connected layer to generate the final SOH estimate. Comparative experiments with four baseline models demonstrate that the proposed time–frequency fusion architecture significantly enhances prediction accuracy, and that each component makes a meaningful contribution to the overall performance.