On partitioning of an SHM problem and parallels with transfer learning

TL;DR

This paper explores a problem-splitting and transfer learning approach to improve damage localization accuracy on an aircraft wing in structural health monitoring, addressing data scarcity and class separation issues.

Contribution

It introduces a novel problem-splitting scheme and applies transfer learning ideas to enhance neural network performance in damage detection tasks.

Findings

Splitting the problem improves classification accuracy.

Transfer learning enhances feature separation and convergence speed.

The approach effectively addresses data scarcity and complex damage cases.

Abstract

In the current work, a problem-splitting approach and a scheme motivated by transfer learning is applied to a structural health monitoring problem. The specific problem in this case is that of localising damage on an aircraft wing. The original experiment is described, together with the initial approach, in which a neural network was trained to localise damage. The results were not ideal, partly because of a scarcity of training data, and partly because of the difficulty in resolving two of the damage cases. In the current paper, the problem is split into two sub-problems and an increase in classification accuracy is obtained. The sub-problems are obtained by separating out the most difficult-to-classify damage cases. A second approach to the problem is considered by adopting ideas from transfer learning (usually applied in much deeper) networks to see if a network trained on the simpler damage cases can help with feature extraction in the more difficult cases. The transfer of a fixed trained batch of layers between the networks is found to improve classification by making the classes more separable in the feature space and to speed up convergence.