Abstract
This is the third and final paper in a series laying foundations for a theory/methodology of Population-Based Structural Health Monitoring (PBSHM). PBSHM involves utilising knowledge from one set of structures in a population and applying it to a different set, such that predictions about the health states of each member in the population can be performed and improved. Central ideas behind PBSHM are those of knowledge transfer and mapping. In the context of PBSHM, knowledge transfer involves using information from a source domain structure, where labels are known for given feature sets, and mapping these onto the unlabelled feature space of a different, target domain structure. This mapping means a classifier trained on the transformed source domain data will generalise to the unlabelled target domain data; i.e.a classifier built on one structure will generalise to another, making Structural Heath Monitoring (SHM) cost-effective and applicable to a wide range of challenging industrial scenarios. This process of mapping features and labels across source and target domains is defined here via domain adaptation, a subcategory of transfer learning. A mathematical underpinning for when domain adaptation is possible in a structural dynamics context is provided, with reference to topology within a graphical representation of structures. Subsequently, a novel procedure for performing domain adaptation on topologically different structures is outlined.
Highlights
This is the third and final paper in a series proposing foundations for a theory and methodology for Population-Based Structural Health Monitoring (PBSHM); it is preceded by [1,2]
The concept of Population-Based Structural Health Monitoring (PBSHM) is to incorporate the feature and label data from each aeroplane to generate a machine learning-based approach that generalises across the complete fleet for all damage scenarios, especially when many members of the fleet have no labelled data associated with them
With reference to the topology of a graphical representation of a structure, this paper presents a mathematical underpinning for when domain adaptation is possible within the context of PBSHM
Summary
This is the third and final paper in a series proposing foundations for a theory and methodology for Population-Based Structural Health Monitoring (PBSHM); it is preceded by [1,2]. PBSHM is the process of utilising information across a population of structures in order to perform and improve inferences that generalise for the complete population [3] This approach to Structural Health Monitoring (SHM) clearly provides significant benefits; any knowledge, whether about the behaviour of features, or any damage-labelled data, obtained from any other members of the population, aids predictions across the whole population. Leveraging this label knowledge from across a population and mapping it onto a consistent space, means that knowledge transfer is possible, aiding the generation of a general machine learning method for the complete population By utilising these two processes, data-based SHM methods can be generated that are cost-effective and applicable across a wider variety of challenging industrial applications. Conclusions are presented highlighting the effectiveness of a transfer learning approach to PBSHM
Sign-in/Register to view highlights & summary 
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call