Dynamically Weighted Spatiotemporal Fusion for Deep Learning-Based Prediction of EHA Degradation in Aviation Systems

Electro-hydrostatic actuators (EHAs) are increasingly deployed in modern aircraft due to their compact size, fast response, and high power-to-weight ratio. However, existing airborne QAR and EICAS data are typically recorded as independent parameters without explicit correspondence to system health states, making degradation assessment and remaining useful life (RUL) prediction challenging. To address this issue, this paper proposes a spatiotemporal degradation modeling framework, termed PreDyn-ST, based on multivariate time series (MTS) data. The method integrates SimCLR-based contrastive pretraining and a dynamic feature fusion mechanism to capture evolving temporal dependencies and spatial sensor correlations. Specifically, graph convolutional networks (GCNs) incorporating physical connectivity priors are employed for spatial modeling, while a Transformer extracts long-range temporal patterns. A learnable dynamic weighting mechanism adaptively balances spatial and temporal features during training. The adaptive behavior is further analyzed using correlation statistical index (CSI) curves for interpretability. Experimental validation on a self-developed EHA degradation test bench and the C-MAPSS benchmark dataset demonstrates that PreDyn-ST achieves competitive and stable prediction performance. In particular, the method shows robust performance under complex operating conditions such as FD004. These results indicate the effectiveness of the proposed framework for accurate and interpretable degradation modeling in aerospace applications.