Majority of the existing dam deformation monitoring models focus on the prediction of individual displacement, and ignore the spatial correlation of data. In this study, we propose a method dealing with multi-target prediction called the Maximum Correlated Stacking of Single-Target. The proposed method can provide reliable predictions of multi-target simultaneously, while fully exploiting the internal relationships between target variables via the strategy of targets stacking. Moreover, it can be coupled with different existing baseline models for the prediction and anomaly detection of arch dam deformation. Jinping–I arch dam is taken as a case study, where the monitoring displacement of 23 different points are analyzed and modeled simultaneously. Three kernel-based machine learning algorithms (i.e., support vector machine, relevance vector machine, and kernel extreme learning machine) and the partial least squares regression are adopted as baseline models for multi-target regression methods. Compared with the single-target regression and two state-of-the-art multi-target regression methods, the simulated results reveal the higher accuracy of the proposed method. Furthermore, model performance is validated in terms of anomaly detection capability, where two progressive anomalous scenarios (i.e., anomalies of single or multiple points) are investigated. The proposed method can be adapted for the health monitoring of other infrastructures in which multiple responses (e.g., displacement, temperature, or stress) need to be predicted simultaneously.

A roller compacted concrete dam (RCCD) located in Cambodia has been gradually deformed over the operation period (2011–2019), and the creep effect of the dam foundation is significant. In order to make integrity and safety assessments of the dam, it is necessary to know the actual mechanical properties of the foundation. This research proposes an intelligent computational framework for analysing the time-dependent working behaviour of the RCCD combined with viscoelastic finite element methods and advanced software techniques. According to the long-term deformation characteristics of the foundation, the Burgers model is employed to describe the constitutive relation of the bedrock. A finite element formulation describes the relationship between dam deformation and mechanical properties in the creep regime. A structural inverse methodology based on improved parallel grey wolf optimization (IGWO) is developed in order to search and identify viscoelastic parameters of the dam foundation. The nonlinear convergence factor strategy and multi-core parallel computing are introduced to enhance global search capability and improve the accuracy of the optimization algorithm. An example of analysis is performed on a dam section, and the results, which are compared with actual measurements for discussion, demonstrate that the selected constitutive model is reasonable and the designed inverse methodology is feasible. Moreover, the proposed IGWO algorithm is very competitive with other state-of-the-art optimization methods such as basic grey wolf optimization (GWO), particle swarm optimization (PSO) and whale optimization algorithm (WOA) for parameter inversion and real-time problems.

High and steep slopes which have developed fractures and intercalations are a great threat to the operation of dams and reservoirs. In this work, the geological conditions and potential modes of failure of the slope found in the right bank of Suofengying hydropower station are investigated for the slope stability and the results are presented. In order to strengthen the slope, an innovative stabilization scheme is employed. The stabilization techniques include development of anti-shear tunnels, anti-slide piles, anchor cables, concrete support structure, etc. Further, the slope stability and reinforcement effects using various stabilization techniques are studied by using finite element strength reduction method. Moreover, in situ monitoring is carried out and the data obtained is analyzed. From the results, it is observed that the deformations that are detected using multipoint extensometers have decreased after the installation of remedial reinforcements. From the analysis of remedial reinforcement methods, it is found that the most critical reinforcement is the development of anti-shear tunnels. In order to monitor the stresses in stirrups and the propagation of cracks in the anti-shear tunnels, three levels of safety monitoring index are proposed. The safety monitoring index is developed based on the results obtained by the simulation of the process of failure of the reinforced slope. The developed safety monitoring index is further applied to the Suofengying project in order to evaluate the overall stability of the slope. The results obtained by monitoring indicate that the performance of the reinforcement structures is satisfactory and the slope has better stability. The methodology proposed in this work shall be useful for similar projects to obtain stability of slopes.

During the long-term operating period, the mechanical parameters of hydraulic structures and foundation deteriorated gradually because of the environmental factors. In order to evaluate the overall safety and durability, these parameters should be calculated by some accurate analysis methods, which are hindered by slow computational efficiency and optimization performance. The improved deep Q-network (DQN) algorithm combined with the deep neural network (DNN) surrogate model was proposed in this paper to ameliorate the above problems. Through the study cases of different zoning in the dam body and the actual engineering foundation, it is shown that the improved DQN algorithm has a good application effect on inversion analysis of material mechanical parameters in this paper.

The magnitude of leakage in the dam body and its foundation can be used as an important indicator in dam risk management. This study presents a data mining and monitoring framework for safety control of the dam leakage flow. First, the influencing factors in dam leakage flow are investigated. Second, a kernel extreme learning machine (KELM) is trained to predict dam leakage, where the parameters are optimized adaptively by parallel multi-population Jaya algorithm. Finally, a novel global sensitivity analysis is proposed to evaluate the relative importance of each input variable based on the KELM. Monitoring data of leakage flow from the concrete face rockfill dam in a pumped-storage power station is used for modeling and verification. The simulated results of the case study reveal that KELM achieves a satisfactory prediction of the leakage flow. It is also found that the water level fluctuation and rainfall have a significant impact on leakage magnitude. The sensitivity analysis provides a useful qualitative metric of dam leakage, which is of great value for dam safety monitoring and operation.