Knowledge Graph Metric Learning Network for Few-Shot Health Status Assessment

Health status assessment plays an important role in guaranteeing equipment operating safety and reducing maintenance cost. Traditional deep learning (DL) methods require large amounts of labeled samples for training, making them ineffective in most practical scenarios with few-shot labeled samples. To address this challenge, we propose a novel knowledge graph metric learning network (KGMLN) for few-shot health status assessment. We first construct a health status knowledge graph (HSKG) to fuse sensor monitoring data, component data, and prior knowledge, providing a new approach to describe the spatiotemporal characteristics of equipment. Then, even with few-shot samples, our KGMLN effectively extracts spatiotemporal features from the HSKG. This network can embed overall structure and node features of HSKG into low-dimensional vectors, and can learn the similarity of few-shot samples in the vector space. By transforming the health status assessment into a few-shot classification problem in the graph representation space, our model achieves high performance with few-shot labeled samples. Experimental results on public datasets demonstrate that our method is significantly comparable to existing full-shot approaches.