Knowledge Graph Transformer Network for Health Status Assessment

Health status (HS) assessment has important scientific significance and practical value to ensure safe equipment operation and reduce maintenance costs. Graph neural network-based methods extract spatiotemporal features from sensor monitoring data and show great promise. However, such methods focus on monitoring data, to the exclusion of other important data, such as component data or prior knowledge, rendering them unable to accurately characterize the relationships between monitoring data and HS. This article proposes a knowledge graph transformer network (KGTN) for HS assessment. An HS knowledge graph is constructed by integrating monitoring data, component data, and prior knowledge. Meta-paths are utilized to describe the monitoring relationships among heterogeneous data, thereby achieving a comprehensive representation of health status. A KGTN extracts accurate spatiotemporal features from the HSKG, automatically extracting meta-paths closely related to HS, and performs feature transformations to obtain accurate feature representations, which are utilized to classify the HS in a vector space. In experiments on Commercial Modular Aviation Propulsion System Simulation (C-MAPSS) public datasets, the proposed model achieves average improvements of 1.12% in Micro-F1 and 3.08% in Macro-F1 compared with the state-of-the-art baselines.