Probabilistic Inference for Structural Health Monitoring: New Modes of Learning from Data
This work addresses data challenges in SHM for engineering applications, but it is incremental as it adapts existing probabilistic techniques rather than introducing new ones.
The paper tackles the problem of noisy and incomplete data in structural health monitoring (SHM) by proposing probabilistic inference methods, which are adapted through case studies in semi-supervised, active, and multi-task learning to improve robustness and adaptability.
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 the measurements 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 reviewing novel techniques for statistical learning (introduced in previous work), it is argued that probabilistic algorithms offer a natural solution to the modelling of SHM data in practice. In three case-studies, probabilistic methods are adapted for applications to SHM signals -- including semi-supervised learning, active learning, and multi-task learning.