Dam Deformation Interpretation and Prediction Based on a Long Short-Term Memory Model Coupled with an Attention Mechanism

被引:22
作者
Su, Yan [1 ]
Weng, Kailiang [1 ]
Lin, Chuan [1 ]
Chen, Zeqin [2 ]
机构
[1] Fuzhou Univ, Coll Civil Engn, Fuzhou 350108, Peoples R China
[2] State Grid Fujian Elect Power Co Ltd, Elect Power Res Inst, Fuzhou 350007, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 14期
关键词
dam deformation; attention mechanism; long short-term memory; dam safety monitoring; prediction;
D O I
10.3390/app11146625
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
An accurate dam deformation prediction model is vital to a dam safety monitoring system, as it helps assess and manage dam risks. Most traditional dam deformation prediction algorithms ignore the interpretation and evaluation of variables and lack qualitative measures. This paper proposes a data processing framework that uses a long short-term memory (LSTM) model coupled with an attention mechanism to predict the deformation response of a dam structure. First, the random forest (RF) model is introduced to assess the relative importance of impact factors and screen input variables. Secondly, the density-based spatial clustering of applications with noise (DBSCAN) method is used to identify and filter the equipment based abnormal values to reduce the random error in the measurements. Finally, the coupled model is used to focus on important factors in the time dimension in order to obtain more accurate nonlinear prediction results. The results of the case study show that, of all tested methods, the proposed coupled method performed best. In addition, it was found that temperature and water level both have significant impacts on dam deformation and can serve as reliable metrics for dam management.
引用
收藏
页数:21
相关论文
共 32 条
[1]  
[Anonymous], 2021, IEEE Trans. Broadcast.
[2]   Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions [J].
Bello-Cerezo, Raquel ;
Biancon, Francesco ;
Di Maria, Francesco ;
Napoletano, Paolo ;
Smeraldi, Fabrizio .
APPLIED SCIENCES-BASEL, 2019, 9 (04)
[3]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281
[4]   A Novel Hybrid Decomposition-Ensemble Prediction Model for Dam Deformation [J].
Cao, Enhua ;
Bao, Tengfei ;
Gu, Chongshi ;
Li, Hui ;
Liu, Yongtao ;
Hu, Shaopei .
APPLIED SCIENCES-BASEL, 2020, 10 (16)
[5]  
Ester M., 1998, KI, V12, P18
[6]  
Ester M., 1996, P 2 INT C KNOWLEDGE, P226, DOI DOI 10.5555/3001460.3001507
[7]   Optimization of RNN-Based Speech Activity Detection [J].
Gelly, Gregory ;
Gauvain, Jean-Luc .
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (03) :646-656
[8]  
HARTLEY GA, 1974, J STRUCT DIV-ASCE, V100, P51
[9]   Displacement Model for Concrete Dam Safety Monitoring via Gaussian Process Regression Considering Extreme Air Temperature [J].
Kang, Fei ;
Li, Junjie .
JOURNAL OF STRUCTURAL ENGINEERING, 2020, 146 (01)
[10]   Monitoring of long-term static deformation data of Fei-Tsui arch dam using artificial neural network-based approaches [J].
Kao, Ching-Yun ;
Loh, Chin-Hsiung .
STRUCTURAL CONTROL & HEALTH MONITORING, 2013, 20 (03) :282-303