Remaining useful life prediction using graph convolutional attention networks with temporal convolution-aware nested residual connections

Degradation of engineered systems can result in poor performance and failure. Graph Convolutional Networks (GCNs) have been used to predict the remaining useful life (RUL) of engineered systems by analyzing condition monitoring data. Conventional GCNs typically stack multiple spectral graph convolutional layers, where each layer aggregates condition monitoring data and then projects the aggregated data into another feature space. However, conventional GCNs suffer from two issues. Firstly, repeated aggregation operations affect the temporal correlation of condition monitoring data. Secondly, repeated aggregation and projection operations may generate less significant features, resulting in poor prediction performance. To address these issues, we introduce a temporal convolutional operation to extract and preserve temporal features prior to repeated aggregation and projection operations. Additionally, we create an internal residual connection to skip some aggregation and projection operations to reduce the negative impact of the less significant features. Finally, we use an attention mechanism to extract the most significant features obtained from previous GCN layers and feed them to next GCN layers. We demonstrate the effectiveness of our method through three case studies. Our numerical results show that the proposed approach outperforms existing data-driven methods.