polito.it
Politecnico di Torino (logo)

Fully automated OMA: from data source integration to results visualization

Alessandro Imperiale

Fully automated OMA: from data source integration to results visualization.

Rel. Emanuele Virgillito, Roberto Proietti, Vittorio Curri, Gabriele Bertagnoli. Politecnico di Torino, NON SPECIFICATO, 2025

Abstract:

Over time, the practice of integrating sensors into engineering works subject to structural monitoring has become standard practice. This has been a real revolution, made necessary by the extraordinary possibilities that this approach offers. Despite the enormous benefits it has brought, the real challenge lies not in the acquisition of data, which is now endless in volume and constantly increasing, but in its interpretation, a task that traditional tools make complex, laborious and often prone to error. This has given rise to the need for a solution capable of operating autonomously, analysing a huge amount of measurements in a very short time without burdening users. This thesis proposes a real paradigm shift, especially when contextualised within the traditional workflow of civil engineering. It describes an innovative system which, thanks to its special architecture, is able to accurately extract key information from an Opera-tional Modal Analysis (OMA). The proposed solution, based on tools that are well-known and verified by industry authorities, overcomes the limitations of established methodol-ogies, which are characterised by laborious, repetitive and dull operations. Compared to the state of the art, the project has evolved from the previous version, enriched with a modern graphical interface for an intuitive and dynamic user experience aimed at study-ing the results. Additional modules that automate the download of raw data directly from provider’s clouds and convert it from its original format to a standardised one, ready for processing, increase the analysis capabilities and power of the software. The new experimental results, compared to past ones, have revealed even more surprising performance: in addition to greater statistical robustness, a drastic reduction in system-atic errors and the elimination of manual inaccuracies; the extraction speed compared to the traditional supervised sequence continues to increase. The final product is an intelli-gent, self-sufficient ecosystem that not only simplifies but revolutionises the entire pro-cess of structural monitoring and analysis.

Relatori: Emanuele Virgillito, Roberto Proietti, Vittorio Curri, Gabriele Bertagnoli
Anno accademico: 2025/26
Tipo di pubblicazione: Elettronica
Numero di pagine: 94
Informazioni aggiuntive: Tesi secretata. Fulltext non presente
Soggetti:
Corso di laurea: NON SPECIFICATO
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-27 - INGEGNERIA DELLE TELECOMUNICAZIONI
Aziende collaboratrici: NON SPECIFICATO
URI: http://webthesis.biblio.polito.it/id/eprint/37776
Modifica (riservato agli operatori) Modifica (riservato agli operatori)