Transfer learning via interpolating structures

TL;DR

This paper introduces a method for transferring knowledge between highly different structures in structural health monitoring by interpolating intermediate models, demonstrated through bridge and aeroplane simulations.

Contribution

It proposes a novel interpolation-based transfer learning approach using intermediate structures to bridge the gap between dissimilar systems in PBSHM.

Findings

Positive transfer achieved between highly-disparate systems

Interpolation of models enables knowledge transfer across different structures

Method demonstrated on bridge and aeroplane simulations

Abstract

Despite recent advances in population-based structural health monitoring (PBSHM), knowledge transfer between highly-disparate structures (i.e., heterogeneous populations) remains a challenge. The current work proposes that heterogeneous transfer may be accomplished via intermediate structures that bridge the gap in information between the structures of interest. A key aspect of the technique is the idea that by varying parameters such as material properties and geometry, one structure can be continuously morphed into another. The approach is demonstrated via a case study involving the parameterisation of (and transfer between) simulated heterogeneous bridge designs (Case 1). Transfer between simplified physical representations of a 'bridge' and 'aeroplane' is then demonstrated in Case 2, via a chain of finite-element models. The facetious question 'When is a bridge not an aeroplane?' has been previously asked in the context of predicting positive transfer based on structural similarity. While the obvious answer to this question is 'Always,' the results presented in the current paper show that, in some cases, positive transfer can indeed be achieved between highly-disparate systems.