Structural health monitoring by combining machine learning and dimensionality reduction techniques

Giacomo Quaranta (1) , Elena Lopez (2) , Emmanuelle Abisset-Chavanne (1, 2) , Jean Louis Duval (3) , Antonio Huerta (4) , Francisco Chinesta (5)

1 ECN - École Centrale de Nantes
2 GeM - Institut de Recherche en Génie Civil et Mécanique
3 ESI Group - ESI Group
4 Departament de Matematica Aplicada III [Barcelona]
5 PIMM - Laboratoire Procédés et Ingénierie en Mécanique et Matériaux

Structural Health Monitoring is of major interest in many areas of structural mechanics. This paper presents a new approach based on the combination of dimensionality reduction and data-mining techniques able to differentiate damaged and undamaged regions in a given structure. Indeed, existence, severity (size) and location of damage can be efficiently estimated from collected data at some locations from which the fields of interest are completed before the analysis based on machine learning and dimensionality reduction techniques proceed.

Mots clés: Non Destructive Testing; Machine Learning; Dimensionality Reduction

Domaines: Sciences de l'ingénieur [physics]

Giacomo Quaranta, Elena Lopez, Emmanuelle Abisset-Chavanne, Jean Louis Duval, Antonio Huerta, et al.. Structural health monitoring by combining machine learning and dimensionality reduction techniques. Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería, 2019, 35 (1), ⟨10.23967/j.rimni.2018.12.001⟩. ⟨hal-02168438⟩