Dam Displacement Research Articles

An Improved Random Forest Model for the Prediction of Dam Displacement

Dam behavior prediction is a classic problem in the monitoring of dam structure. To obtain accurate results, different researchers have established various models. However, the models of predecessors rarely studied the nonlinear characteristics of dam displacement data and the abnormal values of monitoring data. It means that abnormal values will contaminate data set, and consequently reduce the accuracy of model predictions. In this article, an improved Random Forest (RF) model was proposed for analyzing dam displacement prediction and was coupled with a sliding time window strategy. The proposed model is developed by the following steps. First, for the purpose of alleviating the time-lag effect of impact factor phenomenon, a sliding time window strategy was introduced into the RF model to improve the time sensitivity. Second, aiming to determine the hyperparameters, Grid Search (GS) was introduced into RF model to improve the global optimization ability. This article takes masonry arch dam in China as an example, and adopts the horizontal displacement recorded by Global Navigation Satellite Systems (GNSS) as the research object. The accuracy and validity of the proposed model are verified and evaluated based on the evaluation criteria. The simulation results demonstrate that the proposed model could capture the long-term characteristics and provide better prediction based on short-term monitoring data. It also has strong robustness on the abnormal data series, has simpler structures and less parameters, and requires less time for model training, so it can be a potential tool for actual monitoring tasks.

Research on the application of improved SVM model in dam displacement and deformation prediction

Aiming at the influence of dam deformation on many factors, the kernel principal component analysis method is used to compare the factors affecting dam deformation, and the main factors affecting dam deformation are determined. The kernel function of support vector machine is selected, the main influence factor is input, the dam deformation is output, and the optimal parameters are obtained by grid search and cross-verification to establish the model. The deformation results are studied and analyzed, and the prediction effect is evaluated by absolute error and RMSE, and compared with the standard SVM model and the Prophet method based on time series. The results show that the accuracy of support vector machine model is improved obviously by optimizing parameters such as radius of kernel function and penalty factor through mesh optimization, and the prediction accuracy of nonlinear small sample data is significantly higher than that of time series method.

Study on the deformation mechanism of abutment slope and its influence on the dam during the impoundment of high arch dam

The deformation of abutment slope during impoundment poses great challenges to the working behavior and long-term safety of the arch dam. According to the monitoring data of impoundment and slope, slope deformation, valley width change, and arch dam chord length change are systematically analyzed and studied. It is pointed out that the deformation of the dam body and foundation is an irreversible plastic deformation and is evidently correlated with impoundment. Based on the unsaturated effective stress principle of fractured rock mass and the action mode of the reservoir basin pressure, the deformation mechanism of abutment slope has been discussed. The large-scale 3D nonlinear finite element model is established based on numerical analysis, and the deformation mechanism during impoundment and the effect of the effective stress change on the displacement and stress of the dam body are analyzed. The results indicate that effective stress can elucidate the valley contraction to some extent and that the contribution of the reservoir basin pressure is small. Slope deformation is beneficial to the dam displacement to some extent. Moreover, it has a negligible influence on the dam surface stress. However, the junction of the dam and foundation needs to be given special attention.

Multistage Cascade Predictor of Structural Elements Movement in the Deformation Analysis of Large Objects Based on Time Series Influencing Factors

Hydropower dam displacement is influenced by various factors (dam ageing, reservoir water level, air, water, and concrete temperature), which cause complex nonlinear behaviour that is difficult to predict. Object deformation monitoring is a task of geodetic and civil engineers who use different instruments and methods for measurements. Only geodetic methods have been used for the object movement analysis in this research. Although the whole object is affected by the influencing factors, different parts of the object react differently. Hence, one model cannot describe behaviour of every part of the object precisely. In this research, a localised approach is presented—two individual models are developed for every point strategically placed on the object: one model for the analysis and prediction in the direction of the X axis and the other for the Y axis. Additionally, the prediction of horizontal dam movement is not performed directly from measured values of influencing factors, but from predicted values obtained by machine learning and statistical methods. The results of this research show that it is possible to perform accurate short-term time series dam movement prediction by using machine learning and statistical methods and that the only limiting factor for improving prediction length is accurate weather forecast.

Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement

The observation data of dam displacement can reflect the dam’s actual service behavior intuitively. Therefore, the establishment of a precise data-driven model to realize accurate and reliable safety monitoring of dam deformation is necessary. This study proposes a novel probabilistic prediction approach for concrete dam displacement based on optimized relevance vector machine (ORVM). A practical optimization framework for parameters estimation using the parallel Jaya algorithm (PJA) is developed, and various simple kernel/multi-kernel functions of relevance vector machine (RVM) are tested to obtain the optimal selection. The proposed model is tested on radial displacement measurements of a concrete arch dam to mine the effect of hydrostatic, seasonal and irreversible time components on dam deformation. Four algorithms, including support vector regression (SVR), radial basis function neural network (RBF-NN), extreme learning machine (ELM) and the HST-based multiple linear regression (HST-MLR), are used for comparison with the ORVM model. The simulation results demonstrate that the proposed multi-kernel ORVM model has the best performance for predicting the displacement out of range of the used measurements dataset. Meanwhile, the ORVM model has the advantages of probabilistic output and can provide reasonable confidence interval (CI) for dam safety monitoring. This study lays the foundation for the application of RVM in the field of dam health monitoring.

The Prediction of Dam Displacement Time Series Using STL, Extra-Trees, and Stacked LSTM Neural Network

Dam behavior prediction is a fundamental component of dam structural health monitoring. By comparing the predictions and the observations, anomalies can be detected, and then the remedial measures can be executed in time. As the most intuitive monitoring indicators, deformation is often used to evaluate dam structural health status. In this research, we propose a novel combined model for predicting the dam displacement time series. First, the seasonal-trend decomposition based on Loess (STL)method is utilized to decompose the dam displacement time series into seasonal, trend, and remainder components. Then the extremely randomized trees(extra-trees) model is used to predict seasonal components based on the causal models and influencing factors, whereas the stacked Long-Short Term Memory (LSTM)model is used to predict trend and remainder components based on the numerical models and historical observation data. Finally, the predicted results of the three components are aggregated to obtain the total predicted dam displacement. Seven state-of-the-art methods are introduced as benchmark methods to verify the effectiveness and feasibility of the proposed model. To quantitatively evaluate and compare the prediction results, three evaluation indicators, and a statistic test method are introduced. The experimental results show that the proposed model is the best-performing method compared with other benchmark methods both in prediction accuracy and stability. This indicates the proposed novel combined model STL-extra-trees-LSTM is a promising method for predicting displacement time series.

Improve the Model Stability of Dam’s Displacement Prediction Using a Numerical-Statistical Combined Model

In most studies of dam's displacement prediction based on monitoring data, emphasis was given on improving the prediction accuracy, while the model stability was merely considered. This study proposed a numerical-statistical combined model which aims to improve the model stability. The displacement was modelled within three modules: recoverable displacement (i.e., displacement induced by the external load including the water pressure and temperature), non-recoverable displacement (i.e., displacement due to the inherent variations of the materials such as the creep and fatigue of the concrete), and measurement errors (i.e., instrument error and human error). To reduce the random errors and increase the model stability, we used the numerical simulation to constrain the coefficients of explanatory variables for the recoverable displacement. The non-recoverable displacement was estimated by empirical equations, and the measurement errors were given by Gaussian distributions. The randomness of coefficients in the model among all monitoring points are constrained further by random coefficient model. We adopted the root mean square error (RMSE) at varying time and the change ratio of the coefficients (CRC) to evaluate the model stability. Results indicated that the proposed model not only has better prediction accuracy but also has better model stability compared with the statistical model and coordinates-included statistical model proposed in previous studies.

Integrating the Finite Element Method with a Data‐Driven Approach for Dam Displacement Prediction

Both numerical simulations and data‐driven methods have been applied in dam’s displacement modeling. For monitored displacement data‐driven methods, the physical mechanism and structural correlations were rarely discussed. In order to take the spatial and temporal correlations among all monitoring points into account, we took the first step toward integrating the finite element method into a data‐driven model. As the data‐driven method, we selected the random coefficient model, which can make each explanatory variable coefficient of all monitoring points following one or several normal distributions. In this way, explanatory variables are constrained. Another contribution of the proposed model is that the actual elastic modulus at each monitoring point can be back‐calculated. Moreover, with a Lagrange polynomial interpolation, we can obtain the distribution field of elastic modulus, rather than gaining one value for the whole dam in previous studies. The proposed model was validated by a case study of the concrete arch dam in Jinping‐I hydropower station. It has a better prediction precision than the random coefficient model without the finite element method.

Two spatial association–considered mathematical models for diagnosing the long-term balanced relationship and short-term fluctuation of the deformation behaviour of high concrete arch dams

The safety of a high concrete arch dam should be rapidly diagnosed from different angles. Displacement is an actual comprehensive reflection of the arch dam, and it is very important to diagnose the overall deformation behaviour by displacement-based mathematical monitoring models. In this article, based on the spatial association validation of the measured displacement of two high arch dams by the empirical orthogonal function decomposition and the Pearson correlation analysis, two spatial association–considered mathematical models were proposed for the dam displacement of multimonitoring points: one model for the long-term balanced relationship and one model for the short-term fluctuation. To diagnose the abnormality of the dam long-term spatial association, each displacement time series of the multimonitoring points on the dam body with strong spatial associations was decomposed by wavelet multiresolution analysis, and the decomposed high-frequency components, which had the same periodicity as the causal factors of the reservoir water level or air temperature, were determined to establish the cointegration monitoring model. The second model was a combination prediction model, with two sub-models established from the modelling angles of the hydraulic, seasonal and time causal factors and the adjacent point displacement factors, and this second model was mainly used for identifying dam short-term local abnormal deformation behaviour. Engineering examples show that the deformation behaviour of an arch dam under normal conditions has strong spatial associations. The two proposed models have high accuracy and interpreting ability and can effectively reduce the number of needed monitoring models.

Ensemble of bagged regression trees for concrete dam deformation predicting

Tree based ensemble learning algorithms involve generating multiple trees that together produce a consistent prediction and often significantly improving the accuracy of the prediction. In this paper, the technique is further explored, and a dam displacement prediction model based on bootstrap aggregating (bagged) regression trees (BART) is proposed. The case study of concrete dam indicates that the performance of bagged regression trees is better than the conventional regression tree (RT) model in predicting dam displacement. Moreover, the model can also analyze the importance of each variable, which has strong practical value.

Analysis of Dam Behavior by Statistical Models: Application of the Random Forest Approach

Dams are singular infrastructures whose safety assessment requires mathematical models for predicting its behavior and detecting anomalies. Here, we develop an approach based on random forest regression for dam displacement prediction. Random forest regression is a non-parametric statistical technique that can deal with non-linearities and does not need assumptions regarding relationship between predictors. Inputs to the model are the water level in the reservoir, time, and concrete temperature, and the outputs –predicted variables– are movements at the desired points. Since concrete temperature is only available at those points where thermometers are placed, we compute the thermal field at any point of the dam through a one-dimensional deterministic model. Our thermal model accounts for solar radiation, shading, night and evaporative cooling, convection with the air, and long wave radiation exchange. We assess the performance of our model by comparing its estimates with recorded data at a case study, an arch dam located in Algeria, and with outputs computed by two widely used statistical models and an artificial neural network model. Our model provides satisfactory predictions and improves the results of the other models. Our approach is a powerful tool for analyzing dam displacements and incorporates a rigorous evaluation of thermal loads. It emerges as a good alternative for practitioners and stakeholders.

Optimized prediction model for concrete dam displacement based on signal residual amendment

The traditional statistical model of concrete dam's displacement monitoring is used widely in hydraulic engineering. However, the forecasting precision of the conventional calculation model is poor due to the antiquated method of information mining and weak generalization capacity. Furthermore, the uncertain chaos effect implied in residual sequence is also intractable for modeling. In consideration of the nonlinearity, time variation, and unsteadiness of the chaotic characteristics of a dam time series, multiscale wavelet technology is used to decompose and reconstruct the residuals of multiple regression models. The fitting prediction of the low-frequency autocorrelation part is completed through the linear training ability of the autoregressive integrated moving average (ARIMA) model, and the support vector machine (SVM) regression model is constructed to optimize and process the nonlinear high-frequency signal. Then, a combined forecasting model for concrete dam's displacement based on signal residual amendment is established. The analysis of an engineering example indicates that the combined model built in this study can identify the time–frequency nonlinear characteristics of the prototype monitoring signal well, thus improving its fitting precision, antinoise ability, and robustness. In addition, the combined mathematical model established in this study is improved and developed for application to the prediction analysis of the effect quantities of other hydraulic structures.

Gaussian process regression-based forecasting model of dam deformation

The displacement at various measurement points is a critical indicator that can intuitively reflect the operational properties of a dam. It is important to analyse displacement monitoring data in a timely manner and make reliable predictions of dam safety. This paper proposes a GPR-based model for dam displacement forecasting. The input variables of the monitoring model consider hydraulic factors, thermal factors and irreversible factors, and the output variables are the observed displacements of the dam. An example analysis based on the proposed method is performed on a prototype gravity dam, and the performance of different simple/combined covariance functions is investigated to obtain the optimal choice. Compared to multiple linear regression, radial basis function network (RBFN) and support vector machine (SVM) methods, the results indicate that the GPR-based model with a combined covariance function significantly improves the prediction accuracy. The proposed model can effectively overcome the over-learning and poor robustness issues of approaches such as RBFN and SVM. In addition, the GPR-based forecasting model has the advantages of simplicity in the training process and the capacity to provide a probabilistic output.

DAMS DISPLACEMENT AND RESETTLEMENT OF INDIGENOUS PEOPLES IN MALAYSIA: GENDER INSIGHTS AND LESSONS FROM SOME CASE STUDIES

What has gender to do with dams displacement and resettlement? The late social anthropologist Elizabeth Colson through her long-term ethnographic research since the 1950s on forced uprooting by development projects with the Gwembe Tonga of Zambia saw the importance to link gender with the experiences of uprooted women, men and children (cf. Colson 1971, 1999). Yet, in practice, gender continues to be overlooked in many dams and resettlement schemes everywhere. This paper critically reviews issues of dam-induced displacement and resettlement of indigenous communities in Malaysia from a gender lens. It begins by examining resettlement of dam-displaced indigenous communities in Malaysia, particularly in my research areas, to highlight gendered and social consequences, and linkages with ancestral land rights and access to resources. The next section then examines issues of compensation, resettlement and rehabilitation processes. It concludes with gender insights and lessons from my case studies on dam decisions and resettlement processes. The paper argues that dam displacement and resettlement issues are highly gendered, and frequently associated with top-down decisions that seek to legitimise land acquisition of indigenous peoples’ lands in the name of “development”. I thus call on decision makers and implementers to adopt a more responsible and gender-responsive approach to “development”.

基于吸引子特征量的非线性判定法在大坝位移监测数据时间序列中的应用

基于吸引子特征量的非线性判定法在大坝位移监测数据时间序列中的应用

An Improved Long Short‐Term Memory Model for Dam Displacement Prediction

Displacement plays a vital role in dam safety monitoring data, which adequately responds to security risks such as the flood water pressure, extreme temperature, structure deterioration, and bottom bedrock damage. To make accurate predictions, former researchers established various models. However, these models’ input variables cannot efficiently reflect the delays between the external environment and displacement. Therefore, a long short‐term memory (LSTM) model is proposed to make full use of the historical data to reflect the delays. Furthermore, the LSTM model is improved to optimize the performance by making variables more physically reasonable. Finally, a real‐world radial displacement dataset is used to compare the performance of LSTM models, multiple linear regression (MLR), multilayer perceptron (MLP) neural networks, support vector machine (SVM), and boosted regression tree (BRT). The results indicate that (1) the LSTM models can efficiently reflect the delays and make the variables selection more convenient and (2) the improved LSTM model achieves the best performance by optimizing the input form and network structure based on a clearer physical meaning.

Mathematical Modelling of Sayano-Shushenskaya Dam Displacement Process after 2009 Accident

The research presented in the article is of cutting-edge importance because it proves the necessity to develop prognostic mathematical models with the view to studying the behavior of high-head dams for identifying the regularities of their deformations development process and thus providing quantitative definition for the set criteria values of the diagnostic indices to ensure safe operation of such structures. The paper focuses on the peculiarities of building prognostic mathematical models of the dynamic type on the basis of recurrent equations of the 1stand 2ndorders of different types depending on the order of the mathematical model, number of the principal acting factors and discreteness of the input data, with decorrelation of the input actions and sequence of transport delay introduction. It is shown that the properties of the recurrent equation solution in the form of two first conditional moment generating functions of the displacement process of the observed points in the structure delineate a prognostic model which allows predicting the displacements of the observed points. The paper describes the sequence of estimation stages during the creation of prognostic mathematical models in respect to the character of the predictive problem for various time periods of the structure operation. Different combinations of input actions and discreteness of input data, as well as their decorrelation, have been used. We also applied transport delay in order to correctly consider the inertial delay of the dam under different loads. To account for the residual part of the inertial delay, which is affected by random and unaccounted for factors, we used the autoregression model of the process development regularity. To determine the order of the autoregression model, we calculated asymptotically unbiased ratings of the correlation function for the residual error as a difference between the actual and predicted displacements. Methodological specifics of constructing prognostic models have been established in the context of the factors above. Prognostic mathematical models of different types have been developed for the selected period of the dam operation and the results of prediction have been discussed.

Evaluation of the Stability of the Darbandikhan Dam after the 12 November 2017 Mw 7.3 Sarpol-e Zahab (Iran–Iraq Border) Earthquake

We used a global positioning system (GPS), levelling, and Sentinel-1 data to evaluate the stability of the Darbandikhan dam in northeast Iraq after the 2017 Mw 7.3 Sarpol-e Zahab earthquake. GPS and levelling datasets collected in March and November 2017 were used to compute the co-seismic surface displacements of the dam. Sentinel-1 synthetic aperture radar (SAR) images collected between October 2014 and March 2018 were employed to recover the displacement time series of the dam. The large-magnitude displacement gradient on the dam crest hindered the estimation of the co-seismic displacement using this medium-resolution SAR data. However, Sentinel-1 images are sufficient to examine the stability of the dam displacement before and after the earthquake. The results show that the dam was stable between October 2014 and November 2017, but after the earthquake, Sentinel-1 data shows a continuous subsidence of the dam crest between November 2017 and March 2018. To the best knowledge of the authors, this study is the first that utilises InSAR to investigate the behaviour of a dam after a large earthquake.

Dam Safety Evaluation Based on Multiple Linear Regression and Numerical Simulation

The Shimenzi roller-compacted concrete arch dam was built in a soft-rock region with faults and intercalations. The abutments are divided into several potential sliding wedges by major faults and intercalations. In this study, the safety of the dam was analyzed on the basis of measurements of the displacements, strains, and stresses in the concrete. A hydrostatic, temperature, time-displacement model was used to quantify the contributions of water level variations, temperature in the concrete, and time effects, to the dam’s upstream–downstream displacements. A multiple linear regression was used to train and test the relationships among the hydrostatic conditions (temperature, time, and displacements) and to evaluate the dam deformation characteristics and stability. Numerical models of dam stresses were then established and calibrated, which allow quantitative evaluation of dam safety by using statistical methods. The results indicated that (1) the dam is currently in an elastic deformation state; (2) the contribution of temperature to dam displacement differs with elevation; and (3) the state of stress is below the limits of material strength.

Displacement aging component-based stability analysis for the concrete dam

The displacement monitoring data series reconstruction method was developed under equal water level effects based on displacement monitoring data of concrete dams. A dam displacement variation equation was set up under the action of temperature and aging factors by optimized analysis techniques and then the dam displacement hydraulic pressure components can be separated. Through the dynamic adjustment of temperature and aging effect factors, the aging component isolation method of dam displacement was developed. Utilizing the isolated dam displacement aging components, the dam stability model was established. Then, the dam stability criterion was put forward based on convergence and divergence of dam displacement aging components and catastrophe theory. The validity of the proposed method was finally verified combined with the case study.