Innovative deep learning method for predicting the state of health of lithium-ion batteries based on electrochemical impedance spectroscopy and attention mechanisms

Abstract

Electrochemical impedance spectroscopy plays a crucial role in monitoring the state of health of lithium-ion batteries. However, effective feature extraction often relies on limited information and prior knowledge. To address this issue, this paper presents an innovative approach that utilizes the gramian angular field method to transform raw electrochemical impedance spectroscopy data into image data that is easily recognizable by convolutional neural networks. Subsequently, the convolutional block attention module is integrated with bidirectional gated recurrent unit for state of health prediction. First, convolutional block attention module is applied to the electrochemical impedance spectroscopy image data to enhance key features while suppressing redundant information, thereby effectively extracting representative battery state features. Subsequently, the extracted features are fed into a bidirectional gated recurrent unit network for time series modeling to capture the dynamic changes in battery state of health. Experimental results show a significant improvement in the accuracy of state of health predictions, highlighting the effectiveness of convolutional block attention module in feature extraction and the advantages of bidirectional gated recurrent unit in time series forecasting. This research provides an attention mechanism-based feature extraction solution for lithium-ion battery health management, demonstrating the extensive application potential of deep learning in battery state monitoring.