New Modes of Inference for Probabilistic SHM

Abstract

In data-driven SHM, the signals recorded from systems in operation can be noisy and incomplete. Data corresponding to each of the operational, environmental, and damage states are rarely available a priori; furthermore, labelling to describe what each the measured signals represent is often unavailable. In consequence, the algorithms used to implement SHM should be robust and adaptive, while accommodating for missing information in the training-data – such that new information can be included if it becomes available. By collecting three novel techniques for statistical learning (originally proposed in previous work) – including semi-supervised, active, and transfer learning – it is argued that probabilistic algorithms offer a natural solution to model the signals recorded from systems in practice.