Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network
In the field of structural-health monitoring, vibration-based structural damage detection techniques have been practically implemented in recent decades for structural condition assessment. With the development of deep-learning networks that make automatic feature extraction and high classification...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/6/2610 |
| _version_ | 1797541259632443392 |
|---|---|
| author | Jongbin Won Jong-Woong Park Soojin Jang Kyohoon Jin Youngbin Kim |
| author_facet | Jongbin Won Jong-Woong Park Soojin Jang Kyohoon Jin Youngbin Kim |
| author_sort | Jongbin Won |
| collection | DOAJ |
| description | In the field of structural-health monitoring, vibration-based structural damage detection techniques have been practically implemented in recent decades for structural condition assessment. With the development of deep-learning networks that make automatic feature extraction and high classification accuracy possible, deep-learning-based structural damage detection has been gaining significant attention. The deep-learning neural networks come with fixed input and output size, and input data must be downsampled or cropped to the predetermined input size of the networks to obtain desired output of the network. However, the length of input data (i.e., sensing data) is associated with the excitation quality of a structure, adjusting the size of the input data while maintaining the excitation quality is critical to ensure high accuracy of the deep-learning-based structural damage detection. To address this issue, natural-excitation-technique-based data normalization and the use of 1-D convolutional neural networks for automated structural damage detection are presented. The presented approach converts input data to predetermined size using cross-correlation and uses convolutional network to extract damage-sensitive feature for automated structural damage identification. Numerical simulations were conducted on a simply supported beam model excited by random and traffic loadings, and the performance was validated under various scenarios. The proposed method successfully detected the location of damage on a beam under random and traffic loadings with accuracies of 99.90% and 99.20%, respectively. |
| first_indexed | 2024-03-10T13:13:39Z |
| format | Article |
| id | doaj.art-92c268e9b03d405383b71fef60d3e9ee |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:13:39Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-92c268e9b03d405383b71fef60d3e9ee2023-11-21T10:33:57ZengMDPI AGApplied Sciences2076-34172021-03-01116261010.3390/app11062610Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural NetworkJongbin Won0Jong-Woong Park1Soojin Jang2Kyohoon Jin3Youngbin Kim4Department of Civil and Environmental Engineering, Chung-Ang University, Dongjak, Seoul 06974, KoreaDepartment of Civil and Environmental Engineering, Chung-Ang University, Dongjak, Seoul 06974, KoreaDepartment of Image Science and Arts, Chung-Ang University, Dongjak, Seoul 06974, KoreaDepartment of Image Science and Arts, Chung-Ang University, Dongjak, Seoul 06974, KoreaDepartment of Image Science and Arts, Chung-Ang University, Dongjak, Seoul 06974, KoreaIn the field of structural-health monitoring, vibration-based structural damage detection techniques have been practically implemented in recent decades for structural condition assessment. With the development of deep-learning networks that make automatic feature extraction and high classification accuracy possible, deep-learning-based structural damage detection has been gaining significant attention. The deep-learning neural networks come with fixed input and output size, and input data must be downsampled or cropped to the predetermined input size of the networks to obtain desired output of the network. However, the length of input data (i.e., sensing data) is associated with the excitation quality of a structure, adjusting the size of the input data while maintaining the excitation quality is critical to ensure high accuracy of the deep-learning-based structural damage detection. To address this issue, natural-excitation-technique-based data normalization and the use of 1-D convolutional neural networks for automated structural damage detection are presented. The presented approach converts input data to predetermined size using cross-correlation and uses convolutional network to extract damage-sensitive feature for automated structural damage identification. Numerical simulations were conducted on a simply supported beam model excited by random and traffic loadings, and the performance was validated under various scenarios. The proposed method successfully detected the location of damage on a beam under random and traffic loadings with accuracies of 99.90% and 99.20%, respectively.https://www.mdpi.com/2076-3417/11/6/2610deep learningLSTM-FCNstructural damage identificationoptical flowstructural displacement measurement |
| spellingShingle | Jongbin Won Jong-Woong Park Soojin Jang Kyohoon Jin Youngbin Kim Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network Applied Sciences deep learning LSTM-FCN structural damage identification optical flow structural displacement measurement |
| title | Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network |
| title_full | Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network |
| title_fullStr | Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network |
| title_full_unstemmed | Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network |
| title_short | Automated Structural Damage Identification Using Data Normalization and 1-Dimensional Convolutional Neural Network |
| title_sort | automated structural damage identification using data normalization and 1 dimensional convolutional neural network |
| topic | deep learning LSTM-FCN structural damage identification optical flow structural displacement measurement |
| url | https://www.mdpi.com/2076-3417/11/6/2610 |
| work_keys_str_mv | AT jongbinwon automatedstructuraldamageidentificationusingdatanormalizationand1dimensionalconvolutionalneuralnetwork AT jongwoongpark automatedstructuraldamageidentificationusingdatanormalizationand1dimensionalconvolutionalneuralnetwork AT soojinjang automatedstructuraldamageidentificationusingdatanormalizationand1dimensionalconvolutionalneuralnetwork AT kyohoonjin automatedstructuraldamageidentificationusingdatanormalizationand1dimensionalconvolutionalneuralnetwork AT youngbinkim automatedstructuraldamageidentificationusingdatanormalizationand1dimensionalconvolutionalneuralnetwork |