A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning
A method of bridge structure seismic response identification combining signal processing technology and deep learning technology is proposed. The short-time energy method is used to intelligently extract the non-smooth segments in the sensor acquired signals, and the short-time Fourier transform, co...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/399 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587542194552832 |
|---|---|
| author | Zhaoxu Lv Youliang Ding Junxiao Guo |
| author_facet | Zhaoxu Lv Youliang Ding Junxiao Guo |
| author_sort | Zhaoxu Lv |
| collection | DOAJ |
| description | A method of bridge structure seismic response identification combining signal processing technology and deep learning technology is proposed. The short-time energy method is used to intelligently extract the non-smooth segments in the sensor acquired signals, and the short-time Fourier transform, continuous wavelet transform, and Meier frequency cestrum coefficients are used to analyze the spectrum of the non-smooth segments of the response of the bridge structure, and the response feature matrix is extracted and used to classify sequences or images in the LSTM network and the Resnet50 network. The results show that the signal processing techniques can effectively extract the structural response features and reduce the overfitting phenomenon of neural networks, and the combination of signal processing techniques and deep learning techniques can recognize the seismic response of bridge structures with high accuracy and efficiency. |
| format | Article |
| id | doaj-art-fd7b059c3abc4b66bd1e96bf3b317b72 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-fd7b059c3abc4b66bd1e96bf3b317b722025-01-24T13:48:47ZengMDPI AGSensors1424-82202025-01-0125239910.3390/s25020399A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep LearningZhaoxu Lv0Youliang Ding1Junxiao Guo2Jiangsu Xiandai Road & Bridge Co., Ltd., Nanjing 210018, ChinaKey Laboratory of Concrete and Pre-Stressed Concrete Structures of the Ministry of Education, Southeast University, Nanjing 210096, ChinaKey Laboratory of Concrete and Pre-Stressed Concrete Structures of the Ministry of Education, Southeast University, Nanjing 210096, ChinaA method of bridge structure seismic response identification combining signal processing technology and deep learning technology is proposed. The short-time energy method is used to intelligently extract the non-smooth segments in the sensor acquired signals, and the short-time Fourier transform, continuous wavelet transform, and Meier frequency cestrum coefficients are used to analyze the spectrum of the non-smooth segments of the response of the bridge structure, and the response feature matrix is extracted and used to classify sequences or images in the LSTM network and the Resnet50 network. The results show that the signal processing techniques can effectively extract the structural response features and reduce the overfitting phenomenon of neural networks, and the combination of signal processing techniques and deep learning techniques can recognize the seismic response of bridge structures with high accuracy and efficiency.https://www.mdpi.com/1424-8220/25/2/399bridge structuresseismic identificationsignal processingdeep learning |
| spellingShingle | Zhaoxu Lv Youliang Ding Junxiao Guo A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning Sensors bridge structures seismic identification signal processing deep learning |
| title | A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning |
| title_full | A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning |
| title_fullStr | A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning |
| title_full_unstemmed | A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning |
| title_short | A Fast Identification Method for Seismic Responses of Bridge Structures by Integrating Digital Signal Features and Deep Learning |
| title_sort | fast identification method for seismic responses of bridge structures by integrating digital signal features and deep learning |
| topic | bridge structures seismic identification signal processing deep learning |
| url | https://www.mdpi.com/1424-8220/25/2/399 |
| work_keys_str_mv | AT zhaoxulv afastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning AT youliangding afastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning AT junxiaoguo afastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning AT zhaoxulv fastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning AT youliangding fastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning AT junxiaoguo fastidentificationmethodforseismicresponsesofbridgestructuresbyintegratingdigitalsignalfeaturesanddeeplearning |