In view of the complex operational conditions and dynamically changing safety risks associated with high core wall dams in the construction period, a comprehensive safety evaluation system for high core wall dams, which utilizes fuzzy theory and emergency response methods, has been developed. Considering the material zoning, load characteristics, and layout of the safety monitoring system specific to high core wall dams and considering the impacts of flood control capacity, foundation conditions, structural safety, operational status, and slope conditions, a safety evaluation method for high core wall dams on the basis of construction data has been proposed. The model dynamically determines the weights of evaluation factors via evaluation criteria and the term frequency–inverse document frequency (TF–IDF) method. It constructs a comprehensive evaluation subordination feature vector, calculates the degree of match between the current safety evaluation result and historical safety evaluation results, and identifies the matching operational conditions. Finally, on the basis of the risk analysis matrix, the risk level of each tier of evaluation factors is determined, and emergency response measures are formulated. This system provides an online monitoring platform for the operational safety of high core wall dams. This approach enhances the capacity for safety analysis and risk emergency decision-making in hydraulic and hydroelectric engineering.

Federated learning has emerged as a distributed learning paradigm by training at each client and aggregating at a parameter server. System heterogeneity hinders stragglers from responding to the server in time with huge communication costs. Although client grouping in federated learning can solve the straggler problem, the stochastic selection strategy in client grouping neglects the impact of data distribution within each group. Besides, current client grouping approaches make clients suffer unfair participation, leading to biased performances for different clients. In order to guarantee the fairness of client participation and mitigate biased local performances, we propose a federated dynamic client selection method based on data representativity (FedSDR). FedSDR clusters clients into groups correlated with their own local computational efficiency. To estimate the significance of client datasets, we design a novel data representativity evaluation scheme based on local data distribution. Furthermore, the two most representative clients in each group are selected to optimize the global model. Finally, the DYNAMIC-SELECT algorithm updates local computational efficiency and data representativity states to regroup clients after periodic average aggregation. Evaluations on real datasets show that FedSDR improves client participation by 27.4%, 37.9%, and 23.3% compared with FedAvg, TiFL, and FedSS, respectively, taking fairness into account in federated learning. In addition, FedSDR surpasses FedAvg, FedGS, and FedMS by 21.32%, 20.4%, and 6.90%, respectively, in local test accuracy variance, balancing the performance bias of the global model across clients.