Calculating Structure Similarity via a Graph Neural Network in Population-Based Structural Health Monitoring: Part II

Population-based Structural Health Monitoring (PBSHM) aims to gain additional insights on the health of a structure when using data available across a population of similar structures, as compared to the insight available when using only data from a single structure. Before knowledge can be transferred across structures, the similarity between structures (or substructures) within the population must be established. The first paper in this series explored the use of Graph Neural Networks (GNNs), to compute similarity measures via an Irreducible Element (IE) model representation of structures stored within the PBSHM database. While the work explored so far uses a pure topological matching to determine the similarity, this chapter builds upon the aforementioned research and explores the viability of matching using the recently introduced Canonical Form (CF).