State of health and remaining useful life prediction of lithium-ion batteries with conditional graph convolutional network

Graph convolutional networks (GCNs) have been increasingly used to predict the state of health (SOH) and remaining useful life (RUL) of batteries. However, conventional GCNs have limitations. Firstly, the correlation between features and the SOH or RUL is not considered. Secondly, temporal relationships among features are not considered when projecting aggregated temporal features into another dimensional space. To address these issues, two types of undirected graphs are introduced to simultaneously consider the correlation among features and the correlation between features and the SOH or RUL. A conditional GCN is built to analyze these graphs. A dual spectral graph convolutional operation is introduced to analyze the topological structures of these graphs. Additionally, a dilated convolutional operation is integrated with the conditional GCN to consider the temporal correlation among the aggregated features. Two battery datasets are used to evaluate the effectiveness of the proposed method. Experimental results show that the proposed method outperforms other machine learning methods reported in the literature.