Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network
An event of sensor faults in sensor networks deployed in structures might result in the degradation of the structural health monitoring system and lead to difficulties in structural condition assessment. Reconstruction techniques of the data for missing sensor channels were widely adopted to restore...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2737 |
| _version_ | 1827752066356871168 |
|---|---|
| author | Yoon-Soo Shin Junhee Kim |
| author_facet | Yoon-Soo Shin Junhee Kim |
| author_sort | Yoon-Soo Shin |
| collection | DOAJ |
| description | An event of sensor faults in sensor networks deployed in structures might result in the degradation of the structural health monitoring system and lead to difficulties in structural condition assessment. Reconstruction techniques of the data for missing sensor channels were widely adopted to restore a dataset from all sensor channels. In this study, a recurrent neural network (RNN) model combined with external feedback is proposed to enhance the accuracy and effectiveness of sensor data reconstruction for measuring the dynamic responses of structures. The model utilizes spatial correlation rather than spatiotemporal correlation by explicitly feeding the previously reconstructed time series of defective sensor channels back to the input dataset. Because of the nature of spatial correlation, the proposed method generates robust and precise results regardless of the hyperparameters set in the RNN model. To verify the performance of the proposed method, simple RNN, long short-term memory, and gated recurrent unit models were trained using the acceleration datasets obtained from laboratory-scaled three- and six-story shear building frames. |
| first_indexed | 2024-03-11T07:10:29Z |
| format | Article |
| id | doaj.art-757b81cd595a4812b810012a2e92e910 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:29Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-757b81cd595a4812b810012a2e92e9102023-11-17T08:38:59ZengMDPI AGSensors1424-82202023-03-01235273710.3390/s23052737Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural NetworkYoon-Soo Shin0Junhee Kim1Department of Architectural Engineering, Dankook University, Yongin 16890, Republic of KoreaDepartment of Architectural Engineering, Dankook University, Yongin 16890, Republic of KoreaAn event of sensor faults in sensor networks deployed in structures might result in the degradation of the structural health monitoring system and lead to difficulties in structural condition assessment. Reconstruction techniques of the data for missing sensor channels were widely adopted to restore a dataset from all sensor channels. In this study, a recurrent neural network (RNN) model combined with external feedback is proposed to enhance the accuracy and effectiveness of sensor data reconstruction for measuring the dynamic responses of structures. The model utilizes spatial correlation rather than spatiotemporal correlation by explicitly feeding the previously reconstructed time series of defective sensor channels back to the input dataset. Because of the nature of spatial correlation, the proposed method generates robust and precise results regardless of the hyperparameters set in the RNN model. To verify the performance of the proposed method, simple RNN, long short-term memory, and gated recurrent unit models were trained using the acceleration datasets obtained from laboratory-scaled three- and six-story shear building frames.https://www.mdpi.com/1424-8220/23/5/2737structural health monitoringsensor data reconstructionmachine learningrecurrent neural networkexternal feedback |
| spellingShingle | Yoon-Soo Shin Junhee Kim Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network Sensors structural health monitoring sensor data reconstruction machine learning recurrent neural network external feedback |
| title | Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network |
| title_full | Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network |
| title_fullStr | Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network |
| title_full_unstemmed | Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network |
| title_short | Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network |
| title_sort | sensor data reconstruction for dynamic responses of structures using external feedback of recurrent neural network |
| topic | structural health monitoring sensor data reconstruction machine learning recurrent neural network external feedback |
| url | https://www.mdpi.com/1424-8220/23/5/2737 |
| work_keys_str_mv | AT yoonsooshin sensordatareconstructionfordynamicresponsesofstructuresusingexternalfeedbackofrecurrentneuralnetwork AT junheekim sensordatareconstructionfordynamicresponsesofstructuresusingexternalfeedbackofrecurrentneuralnetwork |