Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network
In the field of structural health monitoring (SHM), with the mature development of artificial intelligence, deep learning-based structural damage identification techniques have attracted wide attention. In this paper, the convolutional neural network (CNN) is used to extract the damage feature of si...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/20/10220 |
| _version_ | 1827651921215750144 |
|---|---|
| author | Chuan-Sheng Wu Yang-Xia Peng De-Bing Zhuo Jian-Qiang Zhang Wei Ren Zhen-Yang Feng |
| author_facet | Chuan-Sheng Wu Yang-Xia Peng De-Bing Zhuo Jian-Qiang Zhang Wei Ren Zhen-Yang Feng |
| author_sort | Chuan-Sheng Wu |
| collection | DOAJ |
| description | In the field of structural health monitoring (SHM), with the mature development of artificial intelligence, deep learning-based structural damage identification techniques have attracted wide attention. In this paper, the convolutional neural network (CNN) is used to extract the damage feature of simple supported steel beams. Firstly, the transient dynamic analysis of the steel beam is carried out by finite element software, and the acceleration response signals under different damage scenarios are obtained. Then, the acceleration response signal is decomposed by wavelet packet decomposition (WPD) to extract the wavelet packet band energy ratio variation (ERV) index as the training sample of CNN. Subsequently, the vibration experiment of a simple supported steel beam was carried out, and the results were compared with the numerical simulation results. The characteristic indexes were obtained by making corresponding changes to the vibration signal, and then, the experimental data were input into the CNN to predict the effect of damage detection. The results show that the method can successfully detect the intact structure, single damage, and multiple damages with an accuracy of 95.14% under impact load, and the performance is better than that of support vector machine (SVM), with good robustness. |
| first_indexed | 2024-03-09T20:47:19Z |
| format | Article |
| id | doaj.art-14aae412d9e24f8fa0bc00dac1a17681 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:47:19Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-14aae412d9e24f8fa0bc00dac1a176812023-11-23T22:41:00ZengMDPI AGApplied Sciences2076-34172022-10-0112201022010.3390/app122010220Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural NetworkChuan-Sheng Wu0Yang-Xia Peng1De-Bing Zhuo2Jian-Qiang Zhang3Wei Ren4Zhen-Yang Feng5School of Economics and Management, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Civil Engineering and Architecture, Jishou University, Zhangjiajie 427000, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaHousing and Urban and Rural Construction Commission, Banan District, Chongqing 401320, ChinaIn the field of structural health monitoring (SHM), with the mature development of artificial intelligence, deep learning-based structural damage identification techniques have attracted wide attention. In this paper, the convolutional neural network (CNN) is used to extract the damage feature of simple supported steel beams. Firstly, the transient dynamic analysis of the steel beam is carried out by finite element software, and the acceleration response signals under different damage scenarios are obtained. Then, the acceleration response signal is decomposed by wavelet packet decomposition (WPD) to extract the wavelet packet band energy ratio variation (ERV) index as the training sample of CNN. Subsequently, the vibration experiment of a simple supported steel beam was carried out, and the results were compared with the numerical simulation results. The characteristic indexes were obtained by making corresponding changes to the vibration signal, and then, the experimental data were input into the CNN to predict the effect of damage detection. The results show that the method can successfully detect the intact structure, single damage, and multiple damages with an accuracy of 95.14% under impact load, and the performance is better than that of support vector machine (SVM), with good robustness.https://www.mdpi.com/2076-3417/12/20/10220simple supported steel beamsstructural damage detectionconvolutional neural networkwavelet packet decompositionenergy ratio variation |
| spellingShingle | Chuan-Sheng Wu Yang-Xia Peng De-Bing Zhuo Jian-Qiang Zhang Wei Ren Zhen-Yang Feng Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network Applied Sciences simple supported steel beams structural damage detection convolutional neural network wavelet packet decomposition energy ratio variation |
| title | Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network |
| title_full | Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network |
| title_fullStr | Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network |
| title_full_unstemmed | Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network |
| title_short | Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network |
| title_sort | energy ratio variation based structural damage detection using convolutional neural network |
| topic | simple supported steel beams structural damage detection convolutional neural network wavelet packet decomposition energy ratio variation |
| url | https://www.mdpi.com/2076-3417/12/20/10220 |
| work_keys_str_mv | AT chuanshengwu energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork AT yangxiapeng energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork AT debingzhuo energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork AT jianqiangzhang energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork AT weiren energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork AT zhenyangfeng energyratiovariationbasedstructuraldamagedetectionusingconvolutionalneuralnetwork |