A digital twin framework with MobileNetV2 for damage detection in slab structures
In this study, a digital twin framework is proposed for damage detection in a civil structure, which consists of a finite element model, neural networks, model updating methods, and signal processing. To verify the proposed framework, we present a case study of slab structure using deflection measu...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gruppo Italiano Frattura
2025-02-01
|
| Series: | Fracture and Structural Integrity |
| Subjects: | |
| Online Access: | https://www.fracturae.com/index.php/fis/article/view/5273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856627354173440 |
|---|---|
| author | Huong Duong Nguyen Huan Nguyen Xiaohong Gao |
| author_facet | Huong Duong Nguyen Huan Nguyen Xiaohong Gao |
| author_sort | Huong Duong Nguyen |
| collection | DOAJ |
| description |
In this study, a digital twin framework is proposed for damage detection in a civil structure, which consists of a finite element model, neural networks, model updating methods, and signal processing. To verify the proposed framework, we present a case study of slab structure using deflection measurement as input data. The dynamic characteristics of the physical model are used to calibrate the digital twin model. Damage scenarios are created on the digital twin model. The defection of the damaged slab under static loads is analyzed with two-dimensional discrete wavelet theory (DWT), whereas the diagonal wavelets are used to extract images data set used to train the convolutional neural network (CNN). MobileNetV2 uses transfer learning can reduce the number of trained parameters and hence perform fast convergence. The proposed method gives high accuracy about detection of low-severity damage having the severity less than 10%. There is more than 80% accuracy for predicting the damaged location and its severity. The success of using MobileNetV2 and transfer learning helps to improve the methods further on mobile devices and the potential for more applications. Moreover, the proposed framework does not require the data of the intact structures, leading to much wider applications.
|
| format | Article |
| id | doaj-art-e4f902e561dd4116a66fa6b9f9417df2 |
| institution | Kabale University |
| issn | 1971-8993 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Gruppo Italiano Frattura |
| record_format | Article |
| series | Fracture and Structural Integrity |
| spelling | doaj-art-e4f902e561dd4116a66fa6b9f9417df22025-02-12T06:13:24ZengGruppo Italiano FratturaFracture and Structural Integrity1971-89932025-02-01197210.3221/IGF-ESIS.72.09A digital twin framework with MobileNetV2 for damage detection in slab structuresHuong Duong Nguyen0https://orcid.org/0000-0002-8575-6282Huan Nguyen1Xiaohong Gao2https://orcid.org/0000-0002-8103-6624Middlesex University, London, U.K; Hanoi University of Civil Engineering, Hanoi, VietnamMiddlesex University, London, U.K; International School, Vietnam National University, Hanoi, VietnamMiddlesex University, London, U.K In this study, a digital twin framework is proposed for damage detection in a civil structure, which consists of a finite element model, neural networks, model updating methods, and signal processing. To verify the proposed framework, we present a case study of slab structure using deflection measurement as input data. The dynamic characteristics of the physical model are used to calibrate the digital twin model. Damage scenarios are created on the digital twin model. The defection of the damaged slab under static loads is analyzed with two-dimensional discrete wavelet theory (DWT), whereas the diagonal wavelets are used to extract images data set used to train the convolutional neural network (CNN). MobileNetV2 uses transfer learning can reduce the number of trained parameters and hence perform fast convergence. The proposed method gives high accuracy about detection of low-severity damage having the severity less than 10%. There is more than 80% accuracy for predicting the damaged location and its severity. The success of using MobileNetV2 and transfer learning helps to improve the methods further on mobile devices and the potential for more applications. Moreover, the proposed framework does not require the data of the intact structures, leading to much wider applications. https://www.fracturae.com/index.php/fis/article/view/5273digital twindamage detectionwavelet theoryvibration based damage detectionSHMslab structure |
| spellingShingle | Huong Duong Nguyen Huan Nguyen Xiaohong Gao A digital twin framework with MobileNetV2 for damage detection in slab structures Fracture and Structural Integrity digital twin damage detection wavelet theory vibration based damage detection SHM slab structure |
| title | A digital twin framework with MobileNetV2 for damage detection in slab structures |
| title_full | A digital twin framework with MobileNetV2 for damage detection in slab structures |
| title_fullStr | A digital twin framework with MobileNetV2 for damage detection in slab structures |
| title_full_unstemmed | A digital twin framework with MobileNetV2 for damage detection in slab structures |
| title_short | A digital twin framework with MobileNetV2 for damage detection in slab structures |
| title_sort | digital twin framework with mobilenetv2 for damage detection in slab structures |
| topic | digital twin damage detection wavelet theory vibration based damage detection SHM slab structure |
| url | https://www.fracturae.com/index.php/fis/article/view/5273 |
| work_keys_str_mv | AT huongduongnguyen adigitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures AT huannguyen adigitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures AT xiaohonggao adigitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures AT huongduongnguyen digitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures AT huannguyen digitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures AT xiaohonggao digitaltwinframeworkwithmobilenetv2fordamagedetectioninslabstructures |