Analysis of Concrete Dam Deformation Prediction Based on the ResNet-GRU-SGWO Model
Concrete dam deformation prediction plays a crucial role in ensuring dam safety monitoring. Machine learning, especially recurrent neural networks, plays an important role in this, yet its predictive accuracy is not high. This paper first preprocesses time series data using successive variational mo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Advances in Civil Engineering |
| Online Access: | http://dx.doi.org/10.1155/2024/4791788 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Concrete dam deformation prediction plays a crucial role in ensuring dam safety monitoring. Machine learning, especially recurrent neural networks, plays an important role in this, yet its predictive accuracy is not high. This paper first preprocesses time series data using successive variational mode decomposition (SVMD). Then, it combines residual network (ResNet) and gate recurrent unit (GRU), fully leveraging the excellent information extraction capability of the former and the powerful sequential data processing capability of the latter, proposing the ResNet-GRU model for deformation prediction analysis. During the prediction process, the sanitized gray wolf optimizer (SGWO) algorithm adjusts the parameters, further enhancing the prediction accuracy and performance of the model. The model has also been successfully applied in practical cases, validating its effectiveness. The results indicate that the ResNet-GRU-SGWO model can accurately simulate the dynamic deformation process of concrete dams. Compared with various intelligent prediction models, it achieves the highest prediction accuracy and outstanding performance, providing a reference for the prediction of concrete dam deformation. |
|---|---|
| ISSN: | 1687-8094 |