Multitask learning for improved scour detection: A dynamic wave tank study
This work addresses the problem of structural health monitoring for offshore wind farms, where benign variations among structures make traditional methods less effective, representing an incremental improvement in domain-specific techniques.
The paper tackles the challenge of detecting structural problems like scour in offshore wind farms by using a Bayesian hierarchical model for multitask learning, which infers foundation stiffness parameters at both population and local levels, resulting in more robust anomaly detection compared to a no-pooling approach.
Population-based structural health monitoring (PBSHM), aims to share information between members of a population. An offshore wind (OW) farm could be considered as a population of nominally-identical wind-turbine structures. However, benign variations exist among members, such as geometry, sea-bed conditions and temperature differences. These factors could influence structural properties and therefore the dynamic response, making it more difficult to detect structural problems via traditional SHM techniques. This paper explores the use of a Bayesian hierarchical model as a means of multitask learning, to infer foundation stiffness distribution parameters at both population and local levels. To do this, observations of natural frequency from populations of structures were first generated from both numerical and experimental models. These observations were then used in a partially-pooled Bayesian hierarchical model in tandem with surrogate FE models of the structures to infer foundation stiffness parameters. Finally, it is demonstrated how the learned parameters may be used as a basis to perform more robust anomaly detection (as compared to a no-pooling approach) e.g. as a result of scour.