Structural health monitoring (SHM) is nowadays a significant and topical issue in the civil engineering field, whose first-level task is the damage detection job. Recent advances in artificial intelligence (AI) combined with non-destructive assessments based on output-only vibration signals represent the frontier of SHM. The present research study has handled an AI-based multi-class damage classification task on a numerical benchmark beam problem with three different procedures. The main purpose was to investigate the noise effects of the analyzed damage detection procedures simulating real-world accelerometer sensors. The first damage identification method leverages simple statistical features of vibration signals, whereas the second method additionally considers a subspace-based damage indicator. The third method relies on a dataset composed of a specific set of damage indicators. Two deep learning (DL) techniques have been adopted to compare and verify the results, i.e. a multi-layer perceptron (MLP) and a one-dimensional convolutional network (1D-CNN). Three groups of different reasonable signal-to-noise ratio (SNR) levels were set up to simulate micro electro-mechanical system (MEMS) accelerometer sensors in real-world conditions to evaluate noise effects. In a nutshell, the results demonstrated that the DL models based on stochastic subspace identification (SSI) methods have good noise immunity performance for damage detection purposes.

Noise effects analysis on subspace-based damage detection with neural networks / Rosso, MARCO MARTINO; Aloisio, Angelo; Melchiorre, Jonathan; Huo, Fei; Marano, GIUSEPPE CARLO. - In: STRUCTURES. - ISSN 2352-0124. - ELETTRONICO. - 54:(2023), pp. 23-37. [10.1016/j.istruc.2023.05.024]

Noise effects analysis on subspace-based damage detection with neural networks

Marco Martino Rosso;Jonathan Melchiorre;Giuseppe Carlo Marano
2023

Abstract

Structural health monitoring (SHM) is nowadays a significant and topical issue in the civil engineering field, whose first-level task is the damage detection job. Recent advances in artificial intelligence (AI) combined with non-destructive assessments based on output-only vibration signals represent the frontier of SHM. The present research study has handled an AI-based multi-class damage classification task on a numerical benchmark beam problem with three different procedures. The main purpose was to investigate the noise effects of the analyzed damage detection procedures simulating real-world accelerometer sensors. The first damage identification method leverages simple statistical features of vibration signals, whereas the second method additionally considers a subspace-based damage indicator. The third method relies on a dataset composed of a specific set of damage indicators. Two deep learning (DL) techniques have been adopted to compare and verify the results, i.e. a multi-layer perceptron (MLP) and a one-dimensional convolutional network (1D-CNN). Three groups of different reasonable signal-to-noise ratio (SNR) levels were set up to simulate micro electro-mechanical system (MEMS) accelerometer sensors in real-world conditions to evaluate noise effects. In a nutshell, the results demonstrated that the DL models based on stochastic subspace identification (SSI) methods have good noise immunity performance for damage detection purposes.
2023
File in questo prodotto:
File Dimensione Formato  
Noise_effects_analysis_on_artificial_neural_networks_for_subspace_based_monitoring__first_draft_elsearticle.pdf

embargo fino al 18/05/2024

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 4.14 MB
Formato Adobe PDF
4.14 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Noise effects analysis on subspace-based damage detection with neural networks.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 4.65 MB
Formato Adobe PDF
4.65 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2978945