Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation
For the purpose of maintaining and prolonging the service life of civil constructions, structural damage must be closely monitored. Monitoring the incidence, formation, and spread of damage is crucial to ensure a structure’s ongoing performance. This research proposes a unique approach for multiclas...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/6152 |
| _version_ | 1797590769960222720 |
|---|---|
| author | Pasquale Santaniello Paolo Russo |
| author_facet | Pasquale Santaniello Paolo Russo |
| author_sort | Pasquale Santaniello |
| collection | DOAJ |
| description | For the purpose of maintaining and prolonging the service life of civil constructions, structural damage must be closely monitored. Monitoring the incidence, formation, and spread of damage is crucial to ensure a structure’s ongoing performance. This research proposes a unique approach for multiclass damage detection using acceleration responses based on synchrosqueezing transform (SST) together with deep learning algorithms. In particular, our pipeline is able to classify correctly the time series representing the responses of accelerometers placed on a bridge, which are classified with respect to different types of damage scenarios applied to the bridge. Using benchmark data from the Z24 bridge for multiclass classification for different damage situations, the suggested method is validated. This dataset includes labeled accelerometer measurements from a real-world bridge that has been gradually damaged by various conditions. The findings demonstrate that the suggested approach is successful in exploiting pre-trained 2D convolutional neural networks, obtaining a high classification accuracy that can be further boosted by the application of simple voting methods. |
| first_indexed | 2024-03-11T01:28:06Z |
| format | Article |
| id | doaj.art-245695387297411c92e4bc2469b2784c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:28:06Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-245695387297411c92e4bc2469b2784c2023-11-18T17:31:19ZengMDPI AGSensors1424-82202023-07-012313615210.3390/s23136152Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals RepresentationPasquale Santaniello0Paolo Russo1DIAG Department, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185 Rome, ItalyDIAG Department, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185 Rome, ItalyFor the purpose of maintaining and prolonging the service life of civil constructions, structural damage must be closely monitored. Monitoring the incidence, formation, and spread of damage is crucial to ensure a structure’s ongoing performance. This research proposes a unique approach for multiclass damage detection using acceleration responses based on synchrosqueezing transform (SST) together with deep learning algorithms. In particular, our pipeline is able to classify correctly the time series representing the responses of accelerometers placed on a bridge, which are classified with respect to different types of damage scenarios applied to the bridge. Using benchmark data from the Z24 bridge for multiclass classification for different damage situations, the suggested method is validated. This dataset includes labeled accelerometer measurements from a real-world bridge that has been gradually damaged by various conditions. The findings demonstrate that the suggested approach is successful in exploiting pre-trained 2D convolutional neural networks, obtaining a high classification accuracy that can be further boosted by the application of simple voting methods.https://www.mdpi.com/1424-8220/23/13/6152structural health monitoringdeep learningvibrational damage detectionsynchrosqueezing transformationfeature extraction |
| spellingShingle | Pasquale Santaniello Paolo Russo Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation Sensors structural health monitoring deep learning vibrational damage detection synchrosqueezing transformation feature extraction |
| title | Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation |
| title_full | Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation |
| title_fullStr | Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation |
| title_full_unstemmed | Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation |
| title_short | Bridge Damage Identification Using Deep Neural Networks on Time–Frequency Signals Representation |
| title_sort | bridge damage identification using deep neural networks on time frequency signals representation |
| topic | structural health monitoring deep learning vibrational damage detection synchrosqueezing transformation feature extraction |
| url | https://www.mdpi.com/1424-8220/23/13/6152 |
| work_keys_str_mv | AT pasqualesantaniello bridgedamageidentificationusingdeepneuralnetworksontimefrequencysignalsrepresentation AT paolorusso bridgedamageidentificationusingdeepneuralnetworksontimefrequencysignalsrepresentation |