Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes
This paper aims to locate damaged rods in a three-dimensional (3D) steel truss and reveals some internal working mechanisms of the convolutional neural network (CNN), which is based on the first-order modal parameters and CNN. The CNN training samples (including a large number of damage scenarios) a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/12/4247 |
| _version_ | 1797564581872140288 |
|---|---|
| author | Kefeng Zhong Shuai Teng Gen Liu Gongfa Chen Fangsen Cui |
| author_facet | Kefeng Zhong Shuai Teng Gen Liu Gongfa Chen Fangsen Cui |
| author_sort | Kefeng Zhong |
| collection | DOAJ |
| description | This paper aims to locate damaged rods in a three-dimensional (3D) steel truss and reveals some internal working mechanisms of the convolutional neural network (CNN), which is based on the first-order modal parameters and CNN. The CNN training samples (including a large number of damage scenarios) are created by ABAQUS and PYTHON scripts. The mode shapes and mode curvature differences are taken as the inputs of the CNN training samples, respectively, and the damage locating accuracy of the CNN is investigated. Finally, the features extracted from each convolutional layer of the CNN are checked to reveal some internal working mechanisms of the CNN and explain the specific meanings of some features. The results show that the CNN-based damage detection method using mode shapes as the inputs has a higher locating accuracy for all damage degrees, while the method using mode curvature differences as the inputs has a lower accuracy for the targets with a low damage degree; however, with the increase of the target damage degree, it gradually achieves the same good locating accuracy as mode shapes. The features extracted from each convolutional layer show that the CNN can obtain the difference between the sample to be classified and the average of training samples in shallow layers, and then amplify the difference in the subsequent convolutional layer, which is similar to a power function, finally it produces a distinguishable peak signal at the damage location. Then a damage locating method is derived from the feature extraction of the CNN. All of these results indicate that the CNN using first-order modal parameters not only has a powerful damage location ability, but also opens up a new way to extract damage features from the measurement data. |
| first_indexed | 2024-03-10T18:59:09Z |
| format | Article |
| id | doaj.art-4b757d8e8f814d3e908f31037c51761f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:59:09Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4b757d8e8f814d3e908f31037c51761f2023-11-20T04:29:47ZengMDPI AGApplied Sciences2076-34172020-06-011012424710.3390/app10124247Structural Damage Features Extracted by Convolutional Neural Networks from Mode ShapesKefeng Zhong0Shuai Teng1Gen Liu2Gongfa Chen3Fangsen 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 138632, SingaporeThis paper aims to locate damaged rods in a three-dimensional (3D) steel truss and reveals some internal working mechanisms of the convolutional neural network (CNN), which is based on the first-order modal parameters and CNN. The CNN training samples (including a large number of damage scenarios) are created by ABAQUS and PYTHON scripts. The mode shapes and mode curvature differences are taken as the inputs of the CNN training samples, respectively, and the damage locating accuracy of the CNN is investigated. Finally, the features extracted from each convolutional layer of the CNN are checked to reveal some internal working mechanisms of the CNN and explain the specific meanings of some features. The results show that the CNN-based damage detection method using mode shapes as the inputs has a higher locating accuracy for all damage degrees, while the method using mode curvature differences as the inputs has a lower accuracy for the targets with a low damage degree; however, with the increase of the target damage degree, it gradually achieves the same good locating accuracy as mode shapes. The features extracted from each convolutional layer show that the CNN can obtain the difference between the sample to be classified and the average of training samples in shallow layers, and then amplify the difference in the subsequent convolutional layer, which is similar to a power function, finally it produces a distinguishable peak signal at the damage location. Then a damage locating method is derived from the feature extraction of the CNN. All of these results indicate that the CNN using first-order modal parameters not only has a powerful damage location ability, but also opens up a new way to extract damage features from the measurement data.https://www.mdpi.com/2076-3417/10/12/4247structural state detectionconvolutional neural networksmode shapesmode curvature differencesfeature extraction |
| spellingShingle | Kefeng Zhong Shuai Teng Gen Liu Gongfa Chen Fangsen Cui Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes Applied Sciences structural state detection convolutional neural networks mode shapes mode curvature differences feature extraction |
| title | Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes |
| title_full | Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes |
| title_fullStr | Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes |
| title_full_unstemmed | Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes |
| title_short | Structural Damage Features Extracted by Convolutional Neural Networks from Mode Shapes |
| title_sort | structural damage features extracted by convolutional neural networks from mode shapes |
| topic | structural state detection convolutional neural networks mode shapes mode curvature differences feature extraction |
| url | https://www.mdpi.com/2076-3417/10/12/4247 |
| work_keys_str_mv | AT kefengzhong structuraldamagefeaturesextractedbyconvolutionalneuralnetworksfrommodeshapes AT shuaiteng structuraldamagefeaturesextractedbyconvolutionalneuralnetworksfrommodeshapes AT genliu structuraldamagefeaturesextractedbyconvolutionalneuralnetworksfrommodeshapes AT gongfachen structuraldamagefeaturesextractedbyconvolutionalneuralnetworksfrommodeshapes AT fangsencui structuraldamagefeaturesextractedbyconvolutionalneuralnetworksfrommodeshapes |