Incorporating specialist engineering knowledge into IE models to facilitate enhanced SHM-based transfer learning within PBSHM

Abstract

Population-based Structural Health Monitoring (PBSHM) aims to gather additional knowledge on a structure's health by monitoring multiple structures (the population), compared to the level of knowledge available when utilising only a single structure's data. Before effective transfer learning can occur, a similarity between the structures must be established to prevent negative transfer. Irreducible Element (IE) models, combined with graph theory, are the vehicle used within PBSHM to facilitate this process. Recent research has introduced the Canonical Form (CF) which facilitates a singular IE model per structure; however, detailed IE models solely rely on predefined rules to reduce down to the CF, and do not require the incorporation of specialist engineering knowledge within these reductions. In particular, the specific SHM problem of interest may constrain the reduction. This work aims to enhance the capabilities of IE models by allowing authors to incorporate their specialist engineering knowledge into an IE model. A case study of a steel truss pedestrian bridge is presented, focusing on incorporating the engineering knowledge utilised in its design, construction, and maintenance within an IE model. By enabling authors to leverage their domain expertise, a more comprehensive understanding of structural similarities can be achieved, thereby enhancing transfer learning potential in PBSHM. This paper outlines the methodology and provides insights into the application of domain knowledge in IE models, showcasing its potential benefits for the field.