CNR Author
operator:
and / or
Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2024
Journal article
Open Access
Deep learning and structural health monitoring: temporal fusion transformers for anomaly detection in masonry towers
Falchi F., Girardi M., Gurioli G., Messina N., Padovani C., Pellegrini D.
Detecting anomalies in the vibrational features of age-old buildings is crucial within the Structural Health Monitoring (SHM) framework. The SHM techniques can leverage information from onsite measurements and environmental sources to identify the dynamic properties (such as the frequencies) of the monitored structure, searching for possible deviations or unusual behavior over time. In this paper, the Temporal Fusion Transformer (TFT) network, a deep learning algorithm initially designed for multi-horizon time series forecasting and tested on electricity, traffic, retail, and volatility problems, is applied to SHM. The TFT approach is adopted to investigate the behavior of the Guinigi Tower located in Lucca (Italy) and subjected to a long-term dynamic monitoring campaign. The TFT network is trained on the tower's experimental frequencies enriched with other environmental parameters. The transformer is then employed to predict the vibrational features (natural frequencies, root mean squares values of the velocity time series) and detect possible anomalies or unexpected events by inspecting how much the actual frequencies deviate from the predicted ones. The TFT technique is used to detect the effects of the Viareggio earthquake that occurred on 6 February 2022, and the structural damage induced by three simulated damage scenarios.Source: MECHANICAL SYSTEMS AND SIGNAL PROCESSING, vol. 215 (issue 111382)
DOI: 10.1016/j.ymssp.2024.111382
Metrics:
Falchi F., Girardi M., Gurioli G., Messina N., Padovani C., Pellegrini D.
Detecting anomalies in the vibrational features of age-old buildings is crucial within the Structural Health Monitoring (SHM) framework. The SHM techniques can leverage information from onsite measurements and environmental sources to identify the dynamic properties (such as the frequencies) of the monitored structure, searching for possible deviations or unusual behavior over time. In this paper, the Temporal Fusion Transformer (TFT) network, a deep learning algorithm initially designed for multi-horizon time series forecasting and tested on electricity, traffic, retail, and volatility problems, is applied to SHM. The TFT approach is adopted to investigate the behavior of the Guinigi Tower located in Lucca (Italy) and subjected to a long-term dynamic monitoring campaign. The TFT network is trained on the tower's experimental frequencies enriched with other environmental parameters. The transformer is then employed to predict the vibrational features (natural frequencies, root mean squares values of the velocity time series) and detect possible anomalies or unexpected events by inspecting how much the actual frequencies deviate from the predicted ones. The TFT technique is used to detect the effects of the Viareggio earthquake that occurred on 6 February 2022, and the structural damage induced by three simulated damage scenarios.Source: MECHANICAL SYSTEMS AND SIGNAL PROCESSING, vol. 215 (issue 111382)
DOI: 10.1016/j.ymssp.2024.111382
Metrics:
See at:
CNR IRIS 
| ISTI Repository | www.sciencedirect.com | CNR IRIS 
| CNR IRIS
2023
Journal article
Open Access
The impact of noise on evaluation complexity: the deterministic trust-region case
Bellavia S, Gurioli G, Morini B, Toint Pl
Intrinsic noise in objective function and derivatives evaluations may cause premature termination of optimization algorithms. Evaluation complexity bounds taking this situation into account are presented in the framework of a deterministic trust-region method. The results show that the presence of intrinsic noise may dominate these bounds, in contrast with what is known for methods in which the inexactness in function and derivatives' evaluations is fully controllable. Moreover, the new analysis provides estimates of the optimality level achievable, should noise cause early termination. Numerical experiments are reported that support the theory. The analysis finally sheds some light on the impact of inexact computer arithmetic on evaluation complexity.Source: JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS
DOI: 10.1007/s10957-022-02153-5
Metrics:
Bellavia S, Gurioli G, Morini B, Toint Pl
Intrinsic noise in objective function and derivatives evaluations may cause premature termination of optimization algorithms. Evaluation complexity bounds taking this situation into account are presented in the framework of a deterministic trust-region method. The results show that the presence of intrinsic noise may dominate these bounds, in contrast with what is known for methods in which the inexactness in function and derivatives' evaluations is fully controllable. Moreover, the new analysis provides estimates of the optimality level achievable, should noise cause early termination. Numerical experiments are reported that support the theory. The analysis finally sheds some light on the impact of inexact computer arithmetic on evaluation complexity.Source: JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS
DOI: 10.1007/s10957-022-02153-5
Metrics:
See at:
CNR IRIS | link.springer.com | ISTI Repository | CNR IRIS | CNR IRIS
2023
Other
Restricted
Progetto REVOLUTION - Piattaforma open-source orientata ai digital twins: tecniche di digitalizzazione 3D, monitoraggio delle vibrazioni e modellazione agli elementi finiti per la valutazione dello stato di conservazione di edifici storici e infrastrutture civili
Pellegrini D, Girardi M, Gurioli G, Padovani C
Report tecnico scientifico n.1 (attività svolta nel periodo 15 febbarioi 2022 - 15 febbraio 2023).
Pellegrini D, Girardi M, Gurioli G, Padovani C
Report tecnico scientifico n.1 (attività svolta nel periodo 15 febbarioi 2022 - 15 febbraio 2023).
2023
Conference article
Open Access
Long-term monitoring of a masonry tower with wireless accelerometers
Zini G., Marafini F., Monchetti S., Betti M., Facchini L., Bartoli G., Girardi M., Gurioli G., Padovani C., Pellegrini D.
During the last decades, significant efforts have been made to define appropriate Structural Health Monitoring (SHM) frameworks based on the vibration signatures collected by accelerometers. Data-driven approaches are increasingly adopted for damage detection through the identification of anomalies in the distribution of the frequencies. This paper analyzes the long-term monitoring data acquired from a system installed on the Matilde tower in Livorno (Italy). The tower is a historic masonry structure monitored since the end of 2018 using a wireless sensor network developed during the MOSCARDO project.
Zini G., Marafini F., Monchetti S., Betti M., Facchini L., Bartoli G., Girardi M., Gurioli G., Padovani C., Pellegrini D.
During the last decades, significant efforts have been made to define appropriate Structural Health Monitoring (SHM) frameworks based on the vibration signatures collected by accelerometers. Data-driven approaches are increasingly adopted for damage detection through the identification of anomalies in the distribution of the frequencies. This paper analyzes the long-term monitoring data acquired from a system installed on the Matilde tower in Livorno (Italy). The tower is a historic masonry structure monitored since the end of 2018 using a wireless sensor network developed during the MOSCARDO project.
See at:
2023.compdyn.org | CNR IRIS | ISTI Repository | CNR IRIS
2023
Other
Restricted
Structural health monitoring of age-old towers and infrastructures
Gurioli G
Technical report on the activities carried out within the framework of the STRENGTH project.DOI: 10.32079/isti-tr-2023/005
Metrics:
Gurioli G
Technical report on the activities carried out within the framework of the STRENGTH project.DOI: 10.32079/isti-tr-2023/005
Metrics:
2023
Conference article
Open Access
Towards a cloud-based platform for structural health monitoring: implementation and numerical issues
Croce T, Girardi M, Gurioli G, Padovani C, Pellegrini D
Structural Health Monitoring (SHM) is increasingly important in protecting and maintaining architectural heritage. Its main goal is to distinguish ordinary fluctuations in a building's response from other, possibly anomalous, behaviour. SHM starts setting sensors to measure accelerations or velocities and other environmental parameters over time at fixed points of the structure. The time series processing makes it possible to perform modal tracking and damage/anomaly detection while correlating dynamical and environmental parameters. In practice, these activities are conducted separately, using different numerical codes. Thus, the idea is to take the first step to distance from such practice, leveraging the MOSCARDO system, which encompasses a Wireless Sensor Network (WSN) and a platform designed according to a cloud architecture that provides services for storing and processing data from the WSN. We employ a code based on the Stochastic Subspace Identification (SSI) technique to improve the system's capabilities, and we exploit the SSI's theoretical features to get an efficient implementation that will be integrated into the cloud-based platform. This pipeline is here presented considering data collected from a monitoring campaign on the "Matilde donjon" in Livorno (Italy) and reporting preliminary numerical results on the identification of the modal parameters.Source: LECTURE NOTES IN CIVIL ENGINEERING, pp. 610-619. Milano, Italy, 30-08/01-09/2023
DOI: 10.1007/978-3-031-39109-5_62
Metrics:
Croce T, Girardi M, Gurioli G, Padovani C, Pellegrini D
Structural Health Monitoring (SHM) is increasingly important in protecting and maintaining architectural heritage. Its main goal is to distinguish ordinary fluctuations in a building's response from other, possibly anomalous, behaviour. SHM starts setting sensors to measure accelerations or velocities and other environmental parameters over time at fixed points of the structure. The time series processing makes it possible to perform modal tracking and damage/anomaly detection while correlating dynamical and environmental parameters. In practice, these activities are conducted separately, using different numerical codes. Thus, the idea is to take the first step to distance from such practice, leveraging the MOSCARDO system, which encompasses a Wireless Sensor Network (WSN) and a platform designed according to a cloud architecture that provides services for storing and processing data from the WSN. We employ a code based on the Stochastic Subspace Identification (SSI) technique to improve the system's capabilities, and we exploit the SSI's theoretical features to get an efficient implementation that will be integrated into the cloud-based platform. This pipeline is here presented considering data collected from a monitoring campaign on the "Matilde donjon" in Livorno (Italy) and reporting preliminary numerical results on the identification of the modal parameters.Source: LECTURE NOTES IN CIVIL ENGINEERING, pp. 610-619. Milano, Italy, 30-08/01-09/2023
DOI: 10.1007/978-3-031-39109-5_62
Metrics:
See at:
CNR IRIS | link.springer.com | ISTI Repository | CNR IRIS | CNR IRIS
2022
Journal article
Open Access
Trust-region algorithms: probabilistic complexity and intrinsic noise with applications to subsampling techniques
Bellavia S, Gurioli G, Morini B, Toint Phl
A trust-region algorithm is presented for finding approximate minimizers of smooth unconstrained functions whose values and derivatives are subject to random noise. It is shown that, under suitable probabilistic assumptions, the new method finds (in expectation) an epsilon-approximate minimizer of arbitrary order q >= 1 in at most O(epsilon(-(q+1))) inexact evaluations of the function and its derivatives, providing the first such result for general optimality orders. The impact of intrinsic noise limiting the validity of the assumptions is also discussed and it is shown that difficulties are unlikely to occur in the first-order version of the algorithm for sufficiently large gradients. Conversely, should these assumptions fail for specific realizations, then "degraded" optimality guarantees are shown to hold when failure occurs. These conclusions are then discussed and illustrated in the context of subsampling methods for finite-sum optimization. (C) 2022 The Author(s). Published by Elsevier Ltd on behalf of Association of European Operational Research Societies (EURO).Source: EURO JOURNAL ON COMPUTATIONAL OPTIMIZATION, vol. 10 (issue 100043)
DOI: 10.1016/j.ejco.2022.100043
DOI: 10.48550/arxiv.2112.06176
Metrics:
Bellavia S, Gurioli G, Morini B, Toint Phl
A trust-region algorithm is presented for finding approximate minimizers of smooth unconstrained functions whose values and derivatives are subject to random noise. It is shown that, under suitable probabilistic assumptions, the new method finds (in expectation) an epsilon-approximate minimizer of arbitrary order q >= 1 in at most O(epsilon(-(q+1))) inexact evaluations of the function and its derivatives, providing the first such result for general optimality orders. The impact of intrinsic noise limiting the validity of the assumptions is also discussed and it is shown that difficulties are unlikely to occur in the first-order version of the algorithm for sufficiently large gradients. Conversely, should these assumptions fail for specific realizations, then "degraded" optimality guarantees are shown to hold when failure occurs. These conclusions are then discussed and illustrated in the context of subsampling methods for finite-sum optimization. (C) 2022 The Author(s). Published by Elsevier Ltd on behalf of Association of European Operational Research Societies (EURO).Source: EURO JOURNAL ON COMPUTATIONAL OPTIMIZATION, vol. 10 (issue 100043)
DOI: 10.1016/j.ejco.2022.100043
DOI: 10.48550/arxiv.2112.06176
Metrics:
See at:
arXiv.org e-Print Archive | EURO Journal on Computational Optimization | CNR IRIS | ISTI Repository | www.sciencedirect.com | doi.org | CNR IRIS