The safety monitoring information of the dam is an indicator reflecting the operational status of the dam. It is a crucial source for analyzing and assessing the safety state of reservoir dams, possessing strong real-time capabilities to detect anomalies in the dam at the earliest possible time. When using neural networks for predicting and warning dam safety monitoring data, there are issues such as redundant model parameters, difficulty in tuning, and long computation times. This study addresses real-time dam safety warning issues by first employing the Empirical Mode Decomposition (EMD) method to decompose the effective time-dependent factors and construct a dam in a service state analysis model; it also establishes a multi-dimensional time series analysis equation for dam seepage monitoring. Simultaneously, by combining the Sparrow Optimization Algorithm to optimize the LSTM neural network computation process, it reduces the complexity of model parameter selection. The method is compared to other approaches such as RNN, GRU, BP neural networks, and multivariate linear regression, demonstrating high practicality. It can serve as a valuable reference for reservoir dam state prediction and engineering operation management.

A mechanical analysis model of angular contact ball bearings considering rotor deformation and inertial force of rolling elements is established. The research object being the rotor supported by high-speed instrument bearings as the research object, the bearing-rotor systems of cantilever support, and two-end support are analyzed. The effects of rotor structure and bearing internal parameters on bearing support force, stiffness, spin-roll ratio, and internal load distribution are examined. The results show that when the bearingrotor system is subjected to radial loads, due to the deformation of the rotor, the supporting bearings will be subjected to additional moment in addition to the radial load compared to a rigid rotor. With two-end support, the moment load on the bearing increases as the rotor length and hollowness increase. With cantilever support, the rotor hollowness has almost no effect on the radial load of the bearing, while the large rotor hollowness corresponds to large moment load on non-cantilever end bearing and small moment load on cantilever end bearing. Additionally, bearing moment load and radial load on both sides is directly proportional to rotor cantilever length. The maximum contact load of the rolling element is effectively reduced by increasing the initial contact angle and the number of rolling elements of the cantilever end bearing. The angular stiffness and the spin-roll ratio gradually decrease first and then gradually increase as the load ratio (the ratio of the radial load and the moment load) increases and are minimum when the load ratio is 0.67 and 0.61,respectively.

The long-term structural integrity of reservoir-dam systems is essential for ensuring water security, energy supply, and public safety. Underwater structural defects, driven by complex hydraulic and environmental conditions, pose growing threats to the safe operation of large dams. In recent decades, significant progress has been made in underwater inspection, defect detection, and repair technologies, offering viable alternatives to traditional drawdown-based maintenance. This review systematically synthesizes advances in underwater detection and rehabilitation technologies for reservoir-dam systems, focusing on inspection platforms, positioning and navigation methods, defect identification techniques, and underwater repair materials. It critically examines key challenges, including limited transferability of marine-derived technologies, environmental interference, cumulative operational errors, and real-world applicability. This paper further categorizes existing technologies by maturity and proposes problem-oriented research directions to support the development of intelligent, reliable, and field-deployable systems for underwater defect management in large dams.