Statistical modelling for high arch dam deformation during the initial impoundment period

Hu, Jiang; Ma, Feifei

doi:10.1002/stc.2638

Cited by 27 publications

(31 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a dimension reduction method, principal component analysis (PCA) can reduce the dimension of large data sets with minimum information loss, which is suitable for transforming multiple indexes into a few comprehensive indexes. [31][32][33] In recent years, PCA has been more and more widely used in dam health monitoring. The basic steps of principal component analysis are as follows:…”

Section: Statistical Modelsmentioning

confidence: 99%

Separate modeling technique for deformation monitoring of concrete dams

Yin

2022

Structural Health Monitoring

View full text Add to dashboard Cite

Deformation monitoring is an important aspect of safety control for concrete dams. Deformation monitoring models (such as statistical models and hybrid models) are extensively applied to predict concrete dam deformation and derive confidence interval of normal deformation for anomaly detection. Deformation monitoring models for concrete dams mainly consist of hydrostatic component, temperature component, and aging component. The optimum parameters of individual components are simultaneously determined by least square method for monitoring data fitting. Thus, significant over-fitting of deformation monitoring models may be induced by mutual compensation among the parameters of model components. In this paper, the Separate Modeling Technique (SMT) is proposed for mitigating the over-fitting problem of deformation monitoring models for concrete dams. Firstly, the Empirical Mode Decomposition (EMD) is adopted to extract and visualize the aging component of displacement sequence. Proper mathematical formulation of the aging component can be established, and the problem of improperly presupposing the mathematical form of aging component in the process of constructing traditional deformation monitoring models is well addressed. In this study, the hydrostatic component is represented by the Hybrid Response Surface (HRS), which is formulated using numerical simulation with varying water levels and material parameters. The displacement variation caused by water level fluctuation is identified in terms of isothermal conditions and is used to calibrate the material parameters in the HRS. The temperature component is separated through subtracting the hydrostatic and aging components from displacement time series and then is expressed with proper mathematical formulations. Finally, hybrid models for displacement monitoring of concrete dams are established by combining the separately formulated components. The Separate modeling technique is applied to formulate crest displacement of the YL concrete gravity dam. The false alarm rate of displacement monitoring and a new model selection criterion (namely over-fitting coefficient) are adopted to compare various deformation monitoring models. It is shown that the over-fitting levels of deformation monitoring models can be effectively reduced using the SMT. The deformation monitoring models constructed with the SMT are of better accuracy in displacement prediction and present no false alarm of displacement monitoring for the tested period.

show abstract

Section: Statistical Modelsmentioning

confidence: 99%

Separate modeling technique for deformation monitoring of concrete dams

Yin

2022

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…The traditional analysis models for dam deformation monitoring data include statistical model [1,2], deterministic model [3] and hybrid model [4][5][6] and combination model [7,8]. The idea of statistical model is to establish the relationship between environmental variables (such as, water level, temperature, aging, etc.)…”

Section: Introductionmentioning

confidence: 99%

“…Combined model performs nonlinear optimization combination on multiple single models by integrating various useful information to achieve a more reasonable and comprehensive description of mapping relationship, and it can effectively improve fitting and prediction accuracy. The shortcomings of the combination model include: (1) the linear combination model may get unrealistic negative weights for dealing with nonlinear problems; (2) it is very difficult to construct combinatorial functions.…”

Section: Introductionmentioning

confidence: 99%

“…Mata et al [18] presented a methodology for the selection of the thermometers that best represent the thermal effect in the statistical model. Hu et al [1] proposed the special statistical models for the displacements of high arch dams during their initial impoundment periods by improving estimations of the non-stationary thermal and the non-monotonic timedependent effects. Wang et al [19] presented a shape feature-based spatial clustering method for the dam temperature field, and established a displacement monitoring model of concrete dams using the shape feature clustering-based temperature principal component factor.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study on Deformation Prediction Models of Wuqiangxi Concrete Gravity Dam Based on Monitoring Data

Yang¹,

Han²,

Kuang³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

The deformation prediction models of Wuqiangxi concrete gravity dam are developed, including two statistical models and a deep learning model. In the statistical models, the reliable monitoring data are firstly determined with Lahitte criterion; then, the stepwise regression and partial least squares regression models for deformation prediction of concrete gravity dam are constructed in terms of the reliable monitoring data, and the factors of water pressure, temperature and time effect are considered in the models; finally, according to the monitoring data from 2006 to 2020 of five typical measuring points including J 23 (on dam section 24 # ), J 33 (on dam section 4 # ), J 35 (on dam section 8 # ), J 37 (on dam section 12 # ), and J 39 (on dam section 15 # ) located on the crest of Wuqiangxi concrete gravity dam, the settlement curves of the measuring points are obtained with the stepwise regression and partial least squares regression models. A deep learning model is developed based on long short-term memory (LSTM) recurrent neural network. In the LSTM model, two LSTM layers are used, the rectified linear unit function is adopted as the activation function, the input sequence length is 20, and the random search is adopted. The monitoring data for the five typical measuring points from 2006 to 2017 are selected as the training set, and the monitoring data from 2018 to 2020 are taken as the test set. From the results of case study, we can find that (1) the good fitting results can be obtained with the two statistical models; (2) the partial least squares regression algorithm can solve the model with high correlation factors and reasonably explain the factors; (3) the prediction accuracy of the LSTM model increases with increasing the amount of training data. In the deformation prediction of concrete gravity dam, the LSTM model is suggested when there are sufficient training data, while the partial least squares regression method is suggested when the training data are insufficient.

show abstract

“…8 Statistical models based on multiple linear regression (MLR) and its advanced forms, such as stepwise multiple regression, robust regression, or ridge regression, have provided remarkable prediction results. [14][15][16] Simplicity of formulation and speed of execution have been identified as the typical advantages of statistical models. Nevertheless, owing to a certain correlation among water level, temperature, and the effect of time, defects appear with multicollinearity among independent variables, affecting the accuracy of fitting and prediction.…”

Section: Introductionmentioning

confidence: 99%

Structural deformation prediction model based on extreme learning machine algorithm and particle swarm optimization

Jiang

Zhao

2022

Structural Health Monitoring

View full text Add to dashboard Cite

In this paper, an extreme learning machine (ELM) algorithm based on particle swarm optimization (PSO) is proposed to predict structural deformation. Taking an aqueduct located in Tiantai County, Zhejiang, China, as a case study, a series of observations of the aqueduct vertical displacements and crack openings were used to train a neural network. Then, variables representing environmental factors (air temperature), hydraulic factors (water level), and aging were selected as the influence factors input into the prediction model. Finally, the proposed PSO–ELM model was used to predict the vertical deformation and crack opening of the aqueduct, and the predicted results were compared with the monitored values using four evaluation indexes: mean absolute error ( MAE), mean squared error ( MSE), maximum absolute error ( S), and correlation coefficient ( R). The prediction results obtained using the PSO–ELM model were then compared with those obtained using the evolutionary ELM, conventional ELM, back propagation neural network, long short-term memory, and multiple linear regression models. The results indicate that the proposed PSO–ELM model has an evidently superior predictive ability, with higher values of R and lower values of MAE, MSE, and S. The proposed model can therefore be confidently used to serve as a tool similar to a “weather forecast” function to predict the vertical deformation and crack openings of an aqueduct and may be employed for other structural monitoring applications as well.

show abstract

Statistical modelling for high arch dam deformation during the initial impoundment period

Cited by 27 publications

References 33 publications

Separate modeling technique for deformation monitoring of concrete dams

Separate modeling technique for deformation monitoring of concrete dams

Comparative Study on Deformation Prediction Models of Wuqiangxi Concrete Gravity Dam Based on Monitoring Data

Structural deformation prediction model based on extreme learning machine algorithm and particle swarm optimization

Contact Info

Product

Resources

About