Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks
In this paper, a convolutional neural network (CNN) was used to extract the damage features of a steel frame structure. As structural damage could induce changes of the modal parameters of the structure, the convolution operation was used to extract the features of modal parameters, and a classifica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/16/3376 |
| _version_ | 1818536427328110592 |
|---|---|
| author | Shuai Teng Gongfa Chen Gen Liu Jianbin Lv Fangsen Cui |
| author_facet | Shuai Teng Gongfa Chen Gen Liu Jianbin Lv Fangsen Cui |
| author_sort | Shuai Teng |
| collection | DOAJ |
| description | In this paper, a convolutional neural network (CNN) was used to extract the damage features of a steel frame structure. As structural damage could induce changes of the modal parameters of the structure, the convolution operation was used to extract the features of modal parameters, and a classification algorithm was used to judge the damage state of the structure. The finite element method was applied to analyze the free vibration of the steel frame and obtain the first-order modal strain energy for various damage scenarios, which was used as the CNN training sample. Then vibration experiments were carried out, and modal parameters were obtained from the modal analysis of the vibration signals. The experimental data were inputted into the CNN to verify its damage detection capability. The result showed that the CNN was effective in detecting the intact structure, single damage, and multi damages with an accuracy of 100%. For comparison, the same samples were also applied to the traditional back propagation (BP) neural network, which failed to detect the intact structure and multiple-damage cases. It was found that: (1) The proposed CNN could be trained from finite element simulation data and used in real frame structure damage detection, and it performed better in structural damage detection than BP neural networks; (2) the measured data of a real structure could be supplemented by numerical simulation data, and satisfactory results have been demonstrated. |
| first_indexed | 2024-12-11T18:37:49Z |
| format | Article |
| id | doaj.art-44d096f91eac461b87f859809580b9f5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T18:37:49Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-44d096f91eac461b87f859809580b9f52022-12-22T00:54:42ZengMDPI AGApplied Sciences2076-34172019-08-01916337610.3390/app9163376app9163376Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural NetworksShuai Teng0Gongfa Chen1Gen Liu2Jianbin Lv3Fangsen Cui4School of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaInstitute of High-Performance Computing, Agency for Science, Technology and Research, Singapore 999002, SingaporeIn this paper, a convolutional neural network (CNN) was used to extract the damage features of a steel frame structure. As structural damage could induce changes of the modal parameters of the structure, the convolution operation was used to extract the features of modal parameters, and a classification algorithm was used to judge the damage state of the structure. The finite element method was applied to analyze the free vibration of the steel frame and obtain the first-order modal strain energy for various damage scenarios, which was used as the CNN training sample. Then vibration experiments were carried out, and modal parameters were obtained from the modal analysis of the vibration signals. The experimental data were inputted into the CNN to verify its damage detection capability. The result showed that the CNN was effective in detecting the intact structure, single damage, and multi damages with an accuracy of 100%. For comparison, the same samples were also applied to the traditional back propagation (BP) neural network, which failed to detect the intact structure and multiple-damage cases. It was found that: (1) The proposed CNN could be trained from finite element simulation data and used in real frame structure damage detection, and it performed better in structural damage detection than BP neural networks; (2) the measured data of a real structure could be supplemented by numerical simulation data, and satisfactory results have been demonstrated.https://www.mdpi.com/2076-3417/9/16/3376structural damage detectionconvolutional neural networksmodal strain energysteel framefinite element methodvibration experiment |
| spellingShingle | Shuai Teng Gongfa Chen Gen Liu Jianbin Lv Fangsen Cui Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks Applied Sciences structural damage detection convolutional neural networks modal strain energy steel frame finite element method vibration experiment |
| title | Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks |
| title_full | Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks |
| title_fullStr | Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks |
| title_full_unstemmed | Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks |
| title_short | Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks |
| title_sort | modal strain energy based structural damage detection using convolutional neural networks |
| topic | structural damage detection convolutional neural networks modal strain energy steel frame finite element method vibration experiment |
| url | https://www.mdpi.com/2076-3417/9/16/3376 |
| work_keys_str_mv | AT shuaiteng modalstrainenergybasedstructuraldamagedetectionusingconvolutionalneuralnetworks AT gongfachen modalstrainenergybasedstructuraldamagedetectionusingconvolutionalneuralnetworks AT genliu modalstrainenergybasedstructuraldamagedetectionusingconvolutionalneuralnetworks AT jianbinlv modalstrainenergybasedstructuraldamagedetectionusingconvolutionalneuralnetworks AT fangsencui modalstrainenergybasedstructuraldamagedetectionusingconvolutionalneuralnetworks |