Showing papers by "Alessandro Marzani published in 2022"

Deep Learning Approaches for Robust Time of Arrival Estimation in Acoustic Emission Monitoring

Abstract: In this work, different types of artificial neural networks are investigated for the estimation of the time of arrival (ToA) in acoustic emission (AE) signals. In particular, convolutional neural network (CNN) models and a novel capsule neural network are proposed in place of standard statistical strategies which cannot handle, with enough robustness, very noisy scenarios and, thus, cannot be sufficiently reliable when the signal statistics are perturbed by local drifts or outliers. This concept was validated with two experiments: the pure ToA identification capability was firstly assessed on synthetic signals for which a ground truth is available, showing a 10× gain in accuracy when compared to the classical Akaike information criterion (AIC). Then, the same models were tested via experimental data acquired in the framework of a localization problem to identify targets with known coordinates on a square aluminum plate, demonstrating an overreaching precision under significant noise levels.

Blockchain and Web of Things for Structural Health Monitoring Applications: A Proof of Concept

Abstract: Interoperable and secure data management techniques are fundamental for most of large-scale Structural Health Monitoring (SHM) systems. Indeed, given the relevance of SHM critical measurements, data integrity must be protected against tampering or falsifications. In this paper, we propose a four-layer SHM architecture that allows to build an effective data pipeline from sensors to consumer applications, passing through the cloud. The architecture is built on top of the MODRON platform and exploits the recent advances of the W3C Web of Things (WoT) standard for interoperability. We then discuss how third-party services can take benefit of the W3C WoT architecture to retrieve the SHM critical data and to publish them on the Ethereum Blockchain through an SHM-specific Smart Contract, for data protection and traceability purposes. We test the effectiveness of the Smart Contract implementation in terms of latency and costs under simulated workloads.

Geometric and material attenuation of surface acoustic modes in granular media

Abstract: Granular materials can be used in laboratory-scale physical models to simulate and study seismic wave propagation in various unconsolidated, porous heterogeneous media. This is due to the diverse available grain configurations, in terms of their shape, size, and mechanical parameters, which enable the physical and geological modeling of various complex substrates. In this work, an unconsolidated granular medium, made of silica microbeads, featuring a gravity-induced power-law stiffness profile is experimentally tested in a laboratory setting. The objective is to investigate the attenuation mechanisms of vertically polarized seismic waves traveling at the surface of unconsolidated substrates that are characterized by power-law rigidity profiles. Both geometric spreading and material damping due to skeletal dissipation are considered. The understanding of these two attenuation mechanisms is crucial in seismology for properly determining the seismic site response. An electromagnetic shaker is employed to excite the granular medium between 300 and 550 Hz, generating linear modes that are localized near the surface. A densely sampled section is recorded at the surface using a laser vibrometer. The explicit solution of the geometric attenuation law of Rayleigh-like waves in layered media is employed to calculate the geometric spreading function of the vertically polarized surface modes within the granular material. In accordance with recent studies, the dynamics of these small-amplitude multi-modal linear waves can be analysed by considering the granular medium as perfectly continuous and elastic. By performing a non-linear regression analysis on particle displacements, extracted from experimental velocity data, we determine the frequency-dependent attenuation coefficients, which account for the material damping. The findings of this work show that laboratory-scale physical models can be used to study the geometric spreading of vertically polarized seismic waves induced by the soil inhomogeneity and characterize the material damping of the medium.