Accurate prediction and reasonable warning for dam displacement are important contents of dam safety monitoring. However, it is difficult to identify abnormal displacement based on deterministic point prediction results. In response, this paper proposes a model that integrates several strategies to achieve high-precision point prediction and interval prediction of dam displacement. Specifically, the interval prediction of dam displacement is realized in three stages. In the first stage, a displacement prediction model based on Extreme gradient boosting (XGBoost) is constructed. In the second stage, the prediction error sequence of XGBoost model is generated by the residual estimation method proposed in this paper, and the residual prediction model based on artificial neural network (ANN) is constructed through the maximum likelihood estimation method. In the third stage, the interval estimation of the noise sequence composed of the training error of the ANN model is carried out. Finally, the results obtained above are combined to realize the interval prediction of the dam displacement. The performance of the proposed model is verified by the monitoring data of an actual concrete dam. The results show that the hybrid model can not only achieve better point prediction accuracy than the single model, but also provide high quality interval prediction results.
Dam break is an accident that may heavily threat downstream residents' life and property safety, especially in China. As revealed by accident investigation statistics, both flawed organizational behavior and inadequate downstream resident risk awareness have affected the safety risk of reservoir dams. Multiple information transferring mode and dynamic processes perform with the characteristics of social-technical systems. Based on the system dynamics approach, this study proposed a risk causation model aiming for factor interactions involving organizational, human, and technical system levels. The derived simulation model represented the historical risk evolution process of Gouhou reservoir in China and the rationality of the proposed model was verified. To further improve the efficiency of the organizational response and monitor real-time dam safety, a software tool called Dam Emergency Response Aids (DERA) was constructed to evaluate the potential safety benefits of risk control measures, and to overcome the defects of static emergency plans. By integrating relevant professional modules and data, the mobile application (APP) has been applied on the Jinniu Mountain reservoir dam in Nanjing of China and helped to maintain its excellent safety operation until now. It shows that the risk dynamics model proposed can improve the abilities of dam operating management organization for more effective responses under emergency circumstances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.