A Data Loss Recovery Technique Using EMD-BiGRU Algorithm for Structural Health Monitoring
Missing data caused by sensor faults is a common problem in structural health monitoring systems. Due to negative effects, many methods that adopt measured data to infer missing data have been proposed to tackle this problem in previous studies. However, capturing complex correlations from measured...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/d9eec81b31f14cb699fde61b4ec779f5 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Missing data caused by sensor faults is a common problem in structural health monitoring systems. Due to negative effects, many methods that adopt measured data to infer missing data have been proposed to tackle this problem in previous studies. However, capturing complex correlations from measured data remains a significant challenge. In this study, empirical mode decomposition (EMD) combined with a bidirectional gated recurrent unit (BiGRU) is proposed for the recovery of the measured data. The proposed EMD-BiGRU converts the missing data task as predicted task of time sequence. The core of the method is to predict missing data using the raw data and decomposed subsequence as the decomposed subsequence can improve the predicted accuracy. In addition, the BiGRU in the hybrid model can extract the pre-post correlations of subsequence compared with traditional artificial neural networks. Raw acceleration data collected from a three-story structure are used to evaluate the performance of the EMD-BiGRU for missing data imputation. The recovery results of measure data show that the EMD-BiGRU exhibits excellent performance from two perspectives. First, the decomposed subsequence can improve the accuracy of the BiGRU predicted model. Second, the BiGRU outperforms other machine learning algorithms because it captures more microscopic changes of measured data. The experimental analysis suggests that the change patterns of raw measured signal data are complex, and therefore it is significant to extract the features before modeling. |
|---|