Transfer Learning (TL) techniques can be exploited in engineering structures to overcome the main limit of the data-driven approaches for Dynamic Monitoring, i.e. the lack of a labelled dataset for some structural configuration of the monitored systems. A variety of methods can be implemented, but those that enable heterogeneous TL based on Domain Adaptation have proven to be particularly useful, as they allow knowledge to be transferred within a population composed of a wider range of structures. Among them, the Kernelized Bayesian Transfer Learning (KBTL) can be used to improve the knowledge of a less monitored structure exploiting the knowledge of a more monitored one. In this paper the KBTL is assumed to transfer information from an oscillator to a spatial frame of which few observations are available. This is done by comparing the KBTL performance with those of a Support Vector Machine model generated from data representative only of the spatial frame. Both models are trained on datasets composed by natural frequencies of the two systems estimated at different temperature ranges.

Knowledge Transfer between Oscillators and Real Vibrating Structures to Enrich Dynamic Monitoring Datasets / Cavanni, Valeria; Ceravolo, Rosario; Miraglia, Gaetano. - In: RESEARCH AND REVIEW JOURNAL OF NONDESTRUCTIVE TESTING. - ISSN 2941-4989. - ELETTRONICO. - 2:2(2024), pp. 1-8. [10.58286/30525]

Knowledge Transfer between Oscillators and Real Vibrating Structures to Enrich Dynamic Monitoring Datasets

Cavanni, Valeria;Ceravolo, Rosario;Miraglia, Gaetano
2024

Abstract

Transfer Learning (TL) techniques can be exploited in engineering structures to overcome the main limit of the data-driven approaches for Dynamic Monitoring, i.e. the lack of a labelled dataset for some structural configuration of the monitored systems. A variety of methods can be implemented, but those that enable heterogeneous TL based on Domain Adaptation have proven to be particularly useful, as they allow knowledge to be transferred within a population composed of a wider range of structures. Among them, the Kernelized Bayesian Transfer Learning (KBTL) can be used to improve the knowledge of a less monitored structure exploiting the knowledge of a more monitored one. In this paper the KBTL is assumed to transfer information from an oscillator to a spatial frame of which few observations are available. This is done by comparing the KBTL performance with those of a Support Vector Machine model generated from data representative only of the spatial frame. Both models are trained on datasets composed by natural frequencies of the two systems estimated at different temperature ranges.
File in questo prodotto:
File Dimensione Formato  
NDT-701_manuscript 2024- Cavanni et al.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 717.38 kB
Formato Adobe PDF
717.38 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2995807