A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Integrated SHM Systems: Damage Detection Through Unsupervised Learning and Data Fusion
https://orcid.org/http://orcid.org/0000-0001-5557-144X
https://orcid.org/http://orcid.org/0000-0002-5044-8482
One of the most daunting challenges of modern structural engineering concerns the management and maintenance of ageing infrastructure. The technical response to this challenge falls within the framework of structural health monitoring (SHM), which pursues the automated diagnosis and prognosis of structures from continuously acquired sensor data. In the last years, particular attention has been devoted in the literature to ambient vibration-based SHM owing to its minimal intrusiveness and global damage identification capabilities. Nevertheless, the sheer variety of failure mechanisms that large-scale civil engineering structures may experience, some of which may be of local nature, compels the use of integrated SHM systems and data fusion for comprehensive damage identification. As a result, such systems must deal with extensive databases of heterogeneous monitoring data, being the selection of critical features a key step to link signals to decisions. This chapter presents an overview of some of the most recent statistical pattern recognition, data fusion, feature extraction and damage detection techniques for integrated SHM systems. Under an application-oriented philosophy, the theoretical basis and implementation details of these techniques are illustrated through real case studies of Italian historic buildings.
Integrated SHM Systems: Damage Detection Through Unsupervised Learning and Data Fusion
https://orcid.org/http://orcid.org/0000-0001-5557-144X
https://orcid.org/http://orcid.org/0000-0002-5044-8482
One of the most daunting challenges of modern structural engineering concerns the management and maintenance of ageing infrastructure. The technical response to this challenge falls within the framework of structural health monitoring (SHM), which pursues the automated diagnosis and prognosis of structures from continuously acquired sensor data. In the last years, particular attention has been devoted in the literature to ambient vibration-based SHM owing to its minimal intrusiveness and global damage identification capabilities. Nevertheless, the sheer variety of failure mechanisms that large-scale civil engineering structures may experience, some of which may be of local nature, compels the use of integrated SHM systems and data fusion for comprehensive damage identification. As a result, such systems must deal with extensive databases of heterogeneous monitoring data, being the selection of critical features a key step to link signals to decisions. This chapter presents an overview of some of the most recent statistical pattern recognition, data fusion, feature extraction and damage detection techniques for integrated SHM systems. Under an application-oriented philosophy, the theoretical basis and implementation details of these techniques are illustrated through real case studies of Italian historic buildings.
Integrated SHM Systems: Damage Detection Through Unsupervised Learning and Data Fusion
https://orcid.org/http://orcid.org/0000-0001-5557-144X
https://orcid.org/http://orcid.org/0000-0002-5044-8482
One of the most daunting challenges of modern structural engineering concerns the management and maintenance of ageing infrastructure. The technical response to this challenge falls within the framework of structural health monitoring (SHM), which pursues the automated diagnosis and prognosis of structures from continuously acquired sensor data. In the last years, particular attention has been devoted in the literature to ambient vibration-based SHM owing to its minimal intrusiveness and global damage identification capabilities. Nevertheless, the sheer variety of failure mechanisms that large-scale civil engineering structures may experience, some of which may be of local nature, compels the use of integrated SHM systems and data fusion for comprehensive damage identification. As a result, such systems must deal with extensive databases of heterogeneous monitoring data, being the selection of critical features a key step to link signals to decisions. This chapter presents an overview of some of the most recent statistical pattern recognition, data fusion, feature extraction and damage detection techniques for integrated SHM systems. Under an application-oriented philosophy, the theoretical basis and implementation details of these techniques are illustrated through real case studies of Italian historic buildings.
Integrated SHM Systems: Damage Detection Through Unsupervised Learning and Data Fusion
Structural Integrity
Cury, Alexandre (editor) / Ribeiro, Diogo (editor) / Ubertini, Filippo (editor) / Todd, Michael D. (editor) / García-Macías, Enrique (author) / Ubertini, Filippo (author)
Structural Health Monitoring Based on Data Science Techniques ; Chapter: 12 ; 247-268
Structural Integrity ; 21
2021-10-24
22 pages
Article/Chapter (Book)
Electronic Resource
English
Static-based early-damage detection using symbolic data analysis and unsupervised learning methods
| Springer Verlag | 2014
Unsupervised structural damage detection and localization using deep learning and machine learning
| BASE | 2021
Unsupervised Change Detection From Multichannel SAR Data by Markovian Data Fusion
| Online Contents | 2009
Damage‐sensitive feature extraction with stacked autoencoders for unsupervised damage detection
| Wiley | 2021