Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring
Artificial Intelligence applied to Structural Health Monitoring (SHM) has provided considerable advantages in the accuracy and quality of the estimated structural integrity. Nevertheless, several challenges still need to be tackled in the SHM field, which extended the monitoring process beyond the m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/6/2229 |
| _version_ | 1797442353777082368 |
|---|---|
| author | Federica Zonzini Antonio Carbone Francesca Romano Matteo Zauli Luca De Marchi |
| author_facet | Federica Zonzini Antonio Carbone Francesca Romano Matteo Zauli Luca De Marchi |
| author_sort | Federica Zonzini |
| collection | DOAJ |
| description | Artificial Intelligence applied to Structural Health Monitoring (SHM) has provided considerable advantages in the accuracy and quality of the estimated structural integrity. Nevertheless, several challenges still need to be tackled in the SHM field, which extended the monitoring process beyond the mere data analytics and structural assessment task. Besides, one of the open problems in the field relates to the communication layer of the sensor networks since the continuous collection of long time series from multiple sensing units rapidly consumes the available memory resources, and requires complicated protocol to avoid network congestion. In this scenario, the present work presents a comprehensive framework for vibration-based diagnostics, in which data compression techniques are firstly introduced as a means to shrink the dimension of the data to be managed through the system. Then, neural network models solving binary classification problems were implemented for the sake of damage detection, also encompassing the influence of environmental factors in the evaluation of the structural status. Moreover, the potential degradation induced by the usage of low cost sensors on the adopted framework was evaluated: Additional analyses were performed in which experimental data were corrupted with the noise characterizing MEMS sensors. The proposed solutions were tested with experimental data from the Z24 bridge use case, proving that the amalgam of data compression, optimized (i.e., low complexity) machine learning architectures and environmental information allows to attain high classification scores, i.e., accuracy and precision greater than 96% and 95%, respectively. |
| first_indexed | 2024-03-09T12:40:39Z |
| format | Article |
| id | doaj.art-2f3382acd5c94f3b943830b780b2ca27 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:40:39Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2f3382acd5c94f3b943830b780b2ca272023-11-30T22:18:01ZengMDPI AGSensors1424-82202022-03-01226222910.3390/s22062229Machine Learning Meets Compressed Sensing in Vibration-Based MonitoringFederica Zonzini0Antonio Carbone1Francesca Romano2Matteo Zauli3Luca De Marchi4Advanced Research Center on Electronic Systems “Ercole De Castro” (ARCES), University of Bologna, 40136 Bologna, ItalyAdvanced Research Center on Electronic Systems “Ercole De Castro” (ARCES), University of Bologna, 40136 Bologna, ItalyAdvanced Research Center on Electronic Systems “Ercole De Castro” (ARCES), University of Bologna, 40136 Bologna, ItalyAdvanced Research Center on Electronic Systems “Ercole De Castro” (ARCES), University of Bologna, 40136 Bologna, ItalyDepartment of Electrical, Electronic and Information Engineering (DEI), University of Bologna, 40136 Bologna, ItalyArtificial Intelligence applied to Structural Health Monitoring (SHM) has provided considerable advantages in the accuracy and quality of the estimated structural integrity. Nevertheless, several challenges still need to be tackled in the SHM field, which extended the monitoring process beyond the mere data analytics and structural assessment task. Besides, one of the open problems in the field relates to the communication layer of the sensor networks since the continuous collection of long time series from multiple sensing units rapidly consumes the available memory resources, and requires complicated protocol to avoid network congestion. In this scenario, the present work presents a comprehensive framework for vibration-based diagnostics, in which data compression techniques are firstly introduced as a means to shrink the dimension of the data to be managed through the system. Then, neural network models solving binary classification problems were implemented for the sake of damage detection, also encompassing the influence of environmental factors in the evaluation of the structural status. Moreover, the potential degradation induced by the usage of low cost sensors on the adopted framework was evaluated: Additional analyses were performed in which experimental data were corrupted with the noise characterizing MEMS sensors. The proposed solutions were tested with experimental data from the Z24 bridge use case, proving that the amalgam of data compression, optimized (i.e., low complexity) machine learning architectures and environmental information allows to attain high classification scores, i.e., accuracy and precision greater than 96% and 95%, respectively.https://www.mdpi.com/1424-8220/22/6/2229artificial intelligenceMEMS accelerometersmodel-assisted takeness-based compressed sensingoperational modal analysisstructural health monitoring |
| spellingShingle | Federica Zonzini Antonio Carbone Francesca Romano Matteo Zauli Luca De Marchi Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring Sensors artificial intelligence MEMS accelerometers model-assisted takeness-based compressed sensing operational modal analysis structural health monitoring |
| title | Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring |
| title_full | Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring |
| title_fullStr | Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring |
| title_full_unstemmed | Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring |
| title_short | Machine Learning Meets Compressed Sensing in Vibration-Based Monitoring |
| title_sort | machine learning meets compressed sensing in vibration based monitoring |
| topic | artificial intelligence MEMS accelerometers model-assisted takeness-based compressed sensing operational modal analysis structural health monitoring |
| url | https://www.mdpi.com/1424-8220/22/6/2229 |
| work_keys_str_mv | AT federicazonzini machinelearningmeetscompressedsensinginvibrationbasedmonitoring AT antoniocarbone machinelearningmeetscompressedsensinginvibrationbasedmonitoring AT francescaromano machinelearningmeetscompressedsensinginvibrationbasedmonitoring AT matteozauli machinelearningmeetscompressedsensinginvibrationbasedmonitoring AT lucademarchi machinelearningmeetscompressedsensinginvibrationbasedmonitoring |