Giacomo Maria Allora
Structural analysis with data-driven Machine Learning for components with native sensors.
Rel. Giorgio De Pasquale. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Meccanica, 2026
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (7MB) | Preview |
Abstract
Structural health monitoring (SHM) is undergoing a major shift: from traditional surface-mounted sensors, which introduce parasitic mass, wiring complexity, and environmental vulnerability, alternative routes such as highly integrated "smart" components are being sought. By seamlessly incorporating sensors within structural volumes, this approach allows measurement to be performed in direct contact with the point of interest. This work explores the fabrication of such devices using multi-material fused deposition modeling (FDM) and conductive polymer composites (CPCs), where the polymer matrix plays a load-bearing role and conductive inclusions enable piezoresistive self-sensing. Specifically, this research focuses on the design and characterization of a prototype CPC sensor embedded inside an eVTOL landing gear, aimed at predicting structural degradation and thus improving sustainability.
However, the FDM process introduces complex and unpredictable physical phenomena that make traditional analytical modeling and fitting curves unreliable
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
URI
![]() |
Modifica (riservato agli operatori) |
