Deformation Monitoring Model Research Articles

A novel component separation method for deformation monitoring of rockfill dams

High dams are constructed in mountain valley areas with extremely complex geomorphologies, geologies, and operating environments. The dam body and foundation are subjected to large hydraulic loadings and high stress levels, where many factors affect the structural deformation of the dam, making dam safety monitoring and risk assessment difficult. Since dam deformation is critical for evaluating safe operation, a novel dam deformation monitoring model based on the component separation method is proposed, which can provide scientific significance and high application value for operational safety control. The deformation monitoring data include deformation caused by the water level, the temperature, and the time effect. The homologous monitoring sequence points are selected, and a safety monitoring model is proposed based on the physical causes and the independent component signal decomposition technology. First, the aging component can be extracted by using the correlation consistency of a specific measurement point, where the environment is almost the same at the same time of year, such as the temperature and the water level. Then, fast independent component analysis algorithm is applied to further extract the dam deformation induced by the water level and the temperature via correlation analysis. Finally, a deformation monitoring model based on the component separation can be successfully constructed by combining models of the three components. The proposed dam deformation model can overcome problems of large covariance of deformation component, large collinear interference of periodic component separation, and unstable separation. It is further applied to a high face rockfill dam, and the results shows that the multiple correlation coefficient is greater than 0.995 and the mean absolute percentage error is less than 1.37%, demonstrating the high accuracy and stable separation of the components produced by using this model.

Multisource information fusion model for deformation safety monitoring of earth and rock dams based on deep graph feature fusion

Constructing a long-term deformation monitoring model for earth–rock dams that integrates multisource monitoring information is highly important for enhancing the safety state evaluation and monitoring effectiveness of such dams. In this paper, we propose a new health monitoring model named the deformation–seepage–water level multimeasurement point health monitoring (DSW-MPHM) model for earth–rock dams based on deep graph feature fusion. This model fuses coupled seepage, deformation, and water level features from different monitoring sites of the dam body, base, and shoulder. To achieve this goal, we first establish a new module to fuse spatial and temporal features using graph convolutional networks and long short-term memory. Seepage features and water level features are then extracted using graph attention mechanisms. Subsequently, we employ the feature fusion technique, which incorporates principal component analysis and gated fusers, to construct the DSW-MPHM model, which effectively fuses information from multiple sources. This novel approach successfully addresses the issues of information redundancy and the limited reliability of monitoring models. To verify the validity of the model, it is applied to an endoscopic deformation monitoring program of a panel rockfill dam with a height of 185.5 m. The results demonstrate the superior stability and effectiveness of the proposed method compared to those of 10 baseline prediction models. Additionally, the characterization of the seepage and water level features extracted from the model is verified for its reasonableness. Thus, our proposed model is well suited for practical engineering applications.

Construction and selection of deformation monitoring model for high arch dam using separate modeling technique and composite decision criterion

Deformation prediction is important to ensure the safe and stable operation of arch dams. Statistical models are extensively applied in arch dam deformation monitoring models, which generally include hydrostatic pressure component, temperature component, and aging (irrecoverable) component. In traditional statistical models, aging component is misset, which will cause unreasonable mutual compensation of each component, resulting in overfitting of the overall model. In this paper, the deformation model based on separate modeling technology is, therefore, proposed mitigating the overfitting problem caused by misspecification of the expression of the aging component in traditional statistical models. Dam deformation components related to different effects are extracted from the deformation monitoring sequence with improved complete ensemble empirical mode decomposition with adaptive noise algorithm and equal water level condition. The correct components of the monitoring model are constructed separately. On the one hand, the fitting accuracy of the model is reflected by the coefficient of determination (R2); on the other hand, the overfitting degree of the model is quantitatively evaluated by the overfitting coefficient (OC), so that the model with high fitting accuracy and prediction accuracy is determined, that is, the optimal model is selected by using the R2-OC criterion. In this paper, displacement monitoring data from measurement points are used for analysis. The results show that the deformation monitoring model based on the separated modeling technique exhibits higher prediction accuracy and lower false alarm rate. The R2-OC criterion better reflects the degree of overfitting of the monitoring model and the real situation of arch dam monitoring and warning, which improves the accuracy of model selection.

A novel deformation monitoring model for high arch dams using impulse response-based equivalent temperature and machine learning-aided separate modeling

The anatomy of service status through health monitoring models is essential to long-term structural safety. Since deformation is the intuitive representation of the dam's operating condition, it is crucial to investigate the deformation monitoring model with high accuracy and strong interpretability for the safety management of high arch dams. A novel deformation monitoring model is proposed by incorporating impulse response-based equivalent temperature (ET) and machine learning-aided separate modeling technique (SMT). This methodology has three main sources of novelty. First, the impulse response-based equivalent temperature and corresponding temperature component are derived from heat transfer and temperature convolution theories. Then, the model parameters are identified by an improved firefly algorithm. Second, the components in the monitored displacement are progressively stripped out by clustering analysis, separation under equal water level conditions, and a robust signal decomposition technique. Third, the separated deformation components and environmental factors are modeled by the multi-output deep extreme learning machine (DELM) with autoencoder, and the monitoring model ET-SMT-DELM is thus established. The world's highest arch dam is selected to illustrate the proposed model, and the prediction accuracy, early warning performance, component shares, and impulse response mechanism are comprehensively investigated by comparing with several typical baseline models. The results show that the overfitting of the proposed model is reduced, and the prediction and early warning performance is significantly improved. The resulting temperature impulse response function and component shares imply that the interpretability of the model is also enhanced.

Multi-point deformation monitoring model of concrete arch dam based on MVMD and 3D-CNN

It is difficult for single measuring point model to synchronously characterize the spatial correlation of deformation sequence of concrete dam and the similarity of displacements of different measuring points. Considering the limitation of conventional model in dealing with spatial-temporal data structure, In this study, a deep learning technique for multi-point and multi-output deformation prediction of concrete dams is proposed, which is based on Multivariate Variational Mode Decomposition (MVMD) and three-dimensional convolutional neural network (3D-CNN) combined model. Firstly, the multi-point sequence is decomposed into several relatively stable sub-sequences with different frequency scales by MVMD, which reduces the complexity of the multi-point displacement sequence. Then, In order to enhance the model 's ability to fit the time and spatial features of the sequence, the 3D-CNN model is used to predict the decomposed components and reconstruct the displacement data of the measuring points. This study focuses on the principle, process and calculation steps of the proposed model, and verifies the proposed model through the deformation data of three typical measuring points. The test results show that the prediction model proposed in this paper is an effective method for dam deformation prediction.

Prediction of Dam Deformation Using SSA-LSTM Model Based on Empirical Mode Decomposition Method and Wavelet Threshold Noise Reduction

The deformation monitoring information of concrete dams contains some high-frequency components, and the high-frequency components are strongly nonlinear, which reduces the accuracy of dam deformation prediction. In order to solve such problems, this paper proposes a concrete dam deformation monitoring model based on empirical mode decomposition (EMD) combined with wavelet threshold noise reduction and sparrow search algorithm (SSA) optimization of long short-term memory network (LSTM). The model uses EMD combined with wavelet threshold to decompose and denoise the measured deformation data. On this basis, the LSTM model based on SSA optimization is used to mine the nonlinear function relationship between the reconstructed monitoring data and various influencing factors. The engineering example is analyzed and compared with the prediction results of LSTM model and PSO-SVM model. The results show that the mean absolute error (MAE) and root mean square error (RMSE) of the model are 0.05345 and 0.06358, with the complex correlation coefficient R2 of 0.9533 being closer to 1 and a better fit than the other two models. This can effectively mine the relationship in the measured deformation data, and reduce the influence of high-frequency components on the dam prediction accuracy.

A Data-Driven Dam Deformation Forecasting and Interpretation Method Using the Measured Prototypical Temperature Data

Dam deformation is an intuitive and reliable monitoring indicator for dam structural response. With the increase in the service life of the project, the structural response and environmental quantity data collected by the structural health monitoring (SHM) system show a geometric growth trend. The traditional hydraulic-seasonal-time (HST) model shows poor performance in dealing with massive monitoring data due to the multidimensional data collinearity problem and the inaccurate temperature field simulations. To address these problems, this study proposes a data-driven dam deformation monitoring model for dealing with massive monitoring data based on the light gradient boosting tree (LGB) and Bayesian optimization (BO) algorithm. The proposed BO–LGB method can mine the underlying relationship between temperature changes and dam deformation instead of simple harmonic functions. Moreover, LGB is used to simulate the relationship between high-dimensional environmental quantity data and dam displacement changes, and the BO algorithm is used to determine the optimal hyperparameter selection of LGB based on massive monitoring data. A concrete dam in long-term service was used as the case study, and three typical dam displacement monitoring points were used for model training and validation. The experimental results have indicated that the method can properly consider the collinearity in variables, and has a good balance in modeling accuracy and efficiency when dealing with high-dimensional large-scale dam monitoring data. Moreover, the proposed method can explain the contribution difference between different input variables to select the factors with a more significant influence on modeling.

Data-based model with EMD and a new model selection criterion for dam health monitoring

Data-based models are extensively applied in concrete dam health monitoring. In this paper, the Empirical Mode Decomposition (EMD) is adopted to extract and visualize the irreversible component of deformation monitoring sequence. Consequently proper mathematical formulation of the irreversible component of deformation monitoring model for concrete dams can be established, and the problem of improperly assuming the mathematical form of irreversible component when constructing data-based models is well addressed. The periodic component of the deformation time series is modelled by regression and three machine learning algorithms (i.e., Extreme learning machine, Support Vector Machine based on Grid search and Cross-Verification, and Back Propagation Neural Networks optimized by Genetic Algorithm and Simulated Annealing) respectively. The data-based models with the EMD are able to effectively improve the performance of formulating irreversible component of concrete dam deformation and decrease the over-fitting levels. A new model selection criterion, namely Over-fitting coefficient, is proposed for evaluating and selecting the optimum model among candidate monitoring models. The Over-fitting coefficient can better reflect over-fitting levels of individual monitoring models compared to traditional model selection criteria. As a case study, the displacement and strain monitoring data from the YL gravity dam are modeled by data-based models with the EMD and machine learning algorithms. It is shown that data-based models with the EMD are of higher prediction accuracy and lower rate of false alarm in deformation monitoring than traditional models. The Over-fitting coefficient can better reflect over-fitting levels of monitoring models compared to the error measurement criteria and information criteria. The case study highlights the merits of the proposed data-based models and the model selection criterion for health monitoring of concrete dams.

Spatiotemporal hybrid model for concrete arch dam deformation monitoring considering chaotic effect of residual series

Single-measuring point deformation monitoring model is the most popular method in dam health monitoring. Considering that single-point monitoring model cannot comprehensively reflect the overall deformation properties of dams, a spatiotemporal hybrid model of multi-point deformation monitoring for concrete arch dams is proposed. Meanwhile, considering the chaotic effect of residual series, the support vector machine optimized by particle swarm optimization algorithm (PSO-SVM) is adopted to analyze and forecast the residual series. Hence, a spatiotemporal hybrid model for concrete arch dam deformation monitoring considering the chaotic effect of residual series is proposed in the study. Based on the theory of single-measuring point deformation monitoring, a spatiotemporal hybrid model is established by introducing space coordinate and calculating hydraulic component with finite element method. Then, with the good nonlinear processing ability of PSO-SVM, the chaotic effect of residual series is analyzed and predicted by PSO-SVM. Subsequently, a spatiotemporal hybrid model for concrete arch dam deformation monitoring considering chaotic effect of residual series is established by superimposing the residual prediction term with the predicted value of the spatiotemporal hybrid model. Engineering example show that the proposed model has better fitting and predicting precisions compared with the conventional single-point monitoring models, and it can analyze and predict the deformations of multi-point simultaneously. In addition, the proposed model reduces the workload of modelling point by point in single-point monitoring model, which considerably improves the practicality and computational efficiency of deformation-based health monitoring of concrete arch dams.

Modified dam deformation monitoring model considering periodic component contained in residual sequence

Modified dam deformation monitoring model considering periodic component contained in residual sequence

Application of RS-RF Model in Deformation Prediction of Concrete Dam

The high-performance concrete dam deformation prediction model serves as an important reference for structural safety behavior diagnosis, early warning, and scientific decision-making, and it is also one of the guarantee measures to fully exert the benefits of the project. This paper aims at the subjectivity of factor selection, multicollinearity among factors, and poor generalization of the concrete dam deformation monitoring model. It combines rough set and random forest theory to achieve feature attribute reduction, importance evaluation, and high-precision prediction. In terms of rough set and random forest advantages, a concrete dam deformation prediction model based on RS-RF was established. The application of engineering examples shows that the deformation monitoring model of concrete dams based on RS-RF can reduce the influence factor set, give the importance of each factor, and do well than commonly used models based on SVM and RF in prediction accuracy. Therefore, the deformation prediction model of concrete dam based on RS-RF achieves optimization of influence factors, which makes up for the shortcomings of intelligent prediction model in quantitative analysis and prediction generalization, and has strong engineering practicability.

Research on prediction performance of multiple monitoring points model based on support vector machine

The multiple monitoring points model is an important means of dam structure health monitoring. Combined with the strong nonlinear mapping capability of support vector machine, the fitting and prediction accuracy of the model is further improved. According to the point selection of the multiple monitoring points SVM model, five kinds of testing schemes are designed. The influence of points selection on the prediction performance of the model is verified by case analysis. The results show that the predictive ability of multiple monitoring points model based on SVM is greatly affected by the correlation degree of the monitoring points. Therefore, it is very important to reasonably select the point data with high similarity as the training samples for the effective prediction of deformation monitoring model.

Study on Viscoelastic Deformation Monitoring Index of an RCC Gravity Dam in an Alpine Region Using Orthogonal Test Design

The main objective of this study is to present a method of determining viscoelastic deformation monitoring index of a Roller-compacted concrete (RCC) gravity dam in an alpine region. By focusing on a modified deformation monitoring model considering frost heave and back analyzed mechanical parameters of the dam, the working state of viscoelasticity for the dam is illustrated followed by an investigation and designation of adverse load cases using orthogonal test method. Water pressure component is then calculated by finite element method, while temperature, time effect, and frost heave components are obtained through deformation statistical model considering frost heave. The viscoelastic deformation monitoring index is eventually determined by small probability and maximum entropy methods. The results show that (a) with the abnormal probability 1% the dam deformation monitoring index for small probability and maximum entropy methods is 23.703 mm and 22.981 mm, respectively; thus the maximum measured displacement of the dam is less than deformation monitoring index, which indicates that the dam is currently in a state of safety operation and (b) the obtained deformation monitoring index using orthogonal test method is more accurate due to the full consideration of more random factors; the method gained from this study will likely be of use to diagnose the working state for those RCC dams in alpine regions.

Simulation and experiment analysis of dynamic deformation monitoring with the integrated GPS/pseudolite system

The precision of displacement monitoring for deformable objects with global positioning system (GPS) is severely affected in highly occluded spaces, such as urban canyons and surface mines. This phenomenon is attributed to the presence of few visible GPS satellites with poor geometric structures, thus leading to ineffective positioning in severely occluded areas. An integrated GPS/pseudolite positioning technique is proposed in this paper as an effective solution for precision deformation monitoring in the abovementioned areas. This technique can effectively increase the number of visible satellites, optimize their geometric structure, and improve their positioning precision and reliability. This technique has been used in monitoring related deformable objects and has yielded favorable results. However, the majority of current studies have focused on static positioning, whereas dynamic positioning has largely been ignored. Furthermore, dynamic positioning requires further research to eliminate or reduce unmodeled systematic errors (particularly the multipath error). This paper explains the necessity and effectiveness of pseudolite introduction on the basis of the derivation of the basic deduction formula for integrated GPS/pseudolite positioning. Thereafter, the importance of pseudolite location selection by simulated test verification and analyses is discussed. Several methods for estimating and reducing the multipath error of pseudolite, which is affected by slow or small ground surface deformation and shows high spatial correlation, are also presented in this paper. A dynamic deformation monitoring model is proposed on the basis of the moving average method to improve the precision of dynamic positioning. The standard deviations of the baseline vectors in the X, Y, and Z directions are calculated at 14.0, 35.3, and 9.0 mm, respectively, thus indicating that the positioning precision is improved to different degrees in the proposed model compared with that of the separate GPS system (33.8, 54.4, and 22.3 mm for the X, Y, and Z directions, respectively), the integrated GPS/pseudolite dynamic positioning model prior to the elimination of the multipath errors of pseudolites (24.9, 56.4, and 13.3 mm for the X, Y, and Z directions, respectively), and the integrated GPS/pseudolite dynamic positioning model on the basis of the estimation of multipath error parameters (29.7, 47.9, and 17.8 mm for the X, Y, and Z directions, respectively).

Deformation Monitoring Model of Jinping-I Hydropower Station Based on NACA-BP Neural Network

Back Propagation (BP) neural network can learn and store a large number of input-output model nonlinear relationships with simple structure. Niche ant colony algorithm (NACA) combines the ant colony algorithm (ACA) with the niche technology in order to add its local search ability to ACA with preserving the intelligent search ability and robustness of ACA. To optimize predicting model establishment of the dam monitoring data, NACA and BP neural network modeling method are combined to establish a prediction model of horizontal displacement monitoring data. The traditional BP neural network prediction model is established to make a comparison with the NACA. The results show that NACA-BP neural network method can speed up the convergence rate of BP neural network and enhance local search ability and prediction accuracy.

Signal extraction for GPS deformation monitoring in mining survey

The basic signal model of deformation monitoring with GPS was introduced and the main problems of GPS deformation monitoring in mining area were discussed. For the problem of noise signal extraction in GPS deformation monitoring, the Kalman-EMD method was proposed to obtain the effective deformation signal. The reliability and effectiveness of the methodology were tested and verified by analog signal. The results of experiment in Mongolia show that the accuracy of the proposed GPS deformation monitoring model is equivalent to that of level method.

Dam Safety Analysis Based on Stepwise Regression Model

The simulating and predicting analysis model is studied by the deformation monitoring data of Bikou earth-rockfill dam. Based on the least squares method of Statistics principles, the stepwise regression model has been established of earth-rockfill dam deformation displacement, which is used to fit and forecast the measured deformation data sequences of dam. The results shows that the deformation monitoring model of Bikou earth-rockfill dam having higher fitting precision, longer predict cycle, can be better applied to the fitting and prediction of dam deformation monitoring data.

High precision slope deformation monitoring model based on the GPS/Pseudolites technology in open-pit mine

As the number and geometric intensity of visual satellites are susceptible to large slopes in open-pit mines, we propose integration of GPS/Pseudolites (PLs) positioning technology which can increase the number of visible satellites, strengthen the geometric intensity of satellites and provide a precision solution for slope deformation monitoring. However, the un-modeled systematic errors are still the main limiting factors for high precision baseline solution. In order to eliminate the un-modeled systematic error, the Empirical Mode Decomposition (EMD) theory is employed. The multi-scale decomposition and reconstruction architecture are defined here on the basis of the EMD theory and the systematic error mitigation model is demonstrated as well. A standard of the scale selection for the systematic error elimination is given in terms of the mean of the accumulated standardized modes. Thereafter, the scheme of the GPS/PLs baseline solution based on the EMD is suggested. The simulation and experiment results show that the precision factors (DOP) are reduced greatly when PLs is located suitably. The proposed scheme dramatically improves the reliability of ambiguity resolution and the precision of baseline vector after systematic error being eliminated, and provides an effective model for high precision slope deformation monitoring in open-pit mine.