Prediction models are essential in dam crack behavior identification. Prototype monitoring data arrive sequentially in dam safety monitoring. Given such characteristic, sequential learning algorithms are preferred over batch learning algorithms as they do not require retraining whenever new data are received. A new methodology using the genetic optimized online sequential extreme learning machine and bootstrap confidence intervals is proposed as a practical tool for identifying concrete dam crack behavior. First, online sequential extreme learning machine is adopted to build an online prediction model of crack behavior. The characteristic vector of crack behavior, which is taken as the online sequential extreme learning machine input, is extracted by the statistical model. A genetic algorithm is introduced to optimize the input weights and biases of online sequential extreme learning machine. Second, the BC _a method is proposed to produce confidence intervals based on the improved online sequential extreme learning machine prediction. The improved online sequential extreme learning machine for identifying crack behavior is then built. Third, the crack behavior of an actual concrete dam is taken as an example. The capability of the built model for predicting dam crack opening is evaluated. The comparative results demonstrate that the improved online sequential extreme learning machine can provide highly accurate forecasts and reasonably identify crack behavior.

A dam is a complex and important water‐retaining structure. Once the dam is broken, the flood will cause immeasurable damage to the lives and properties of the downstream people, so it is particularly important to have the dam risk management. Since the dam‐break flood is a severe‐consequence low‐frequency event, the corresponding fatalities caused by it are difficult to estimate due to the lack of relevant data and poor data continuity. This paper analyzes the direct and indirect factors affecting the risk of life loss in dam failures and studies the characteristics, distribution rules, and membership functions of each factor. An adaptive differential evolution method is constructed through an optimization of the mutation factors and cross factors of the differential evolution method. This proposed evaluation method also combines with the fuzzy clustering iterative method that is capable of evaluating the similarity of life loss in dam accidents. The effectiveness of the proposed method is verified by 16 dam‐break case studies.

Dam behavior is difficult to predict due to its complexity. At the same time, dam deformation behavior is vital to dam systems. Developing a precise prediction model of dam deformation from prototype data is still challenging but determinant in the structural safety assessment. In this paper, an artificial neural network (ANN), trained by the improved artificial fish swarm algorithm (IAFSA) and backpropagation algorithm (BP), is proposed for predicting the dam deformation. Initially, crossover operator is embedded into AFSA, which aims to enhance the performance. In light of the influence mechanism of many factors on dam deformation behavior, the hybrid (IAFSA and BP) model uses statistical input to obtain the optimal connection weights and threshold values of the neural network. The hybrid model integrates IAFSA’s strong global searching ability and BP’s strong local search ability. To avoid overfitting the training set data, a validation set is adopted to check the generalization capability. Subsequently, the obtained optimal parameters are applied to predict the dam deformation behavior. The hybrid model’s preciseness is verified against the radial displacements of a pendulum in a concrete arch dam and simulations of four models: statistical model, BP-ANN optimized by genetic algorithm (GA), particle swarm optimization (PSO), and AFSA. Results demonstrate that the proposed model outperforms other models and may provide alarms for safety control.

Zeta potential testing, Fourier infrared spectroscopy, and total organic carbon analysis were employed in this manuscript to explore the flocculation mechanism of polyacrylamide (PAM) on slurry with a high content of polycarboxylate ether (PCE). Through the combination of assessments of chemical bond shifts, adsorption indicators, and intrinsic viscosity of high-molecular-weight polymer systems, the microscale flocculation mechanisms of different PAM dosages in cement suspensions were elucidated, showcasing stages of “adsorption–lubrication–entanglement”. Initially (PAM < 0.3%), with PAM introduction, the polymer primarily underwent adsorption interactions, including hydrogen bonding between the ester group, amine group, and water molecules; chelation between the ester group and Ca²⁺ and Al³⁺ on the cement surface; and bridging between PAM’s long-chain structure and cement particles. As the PAM content increased, the cement particles’ adsorption capacity saturated (PAM < 0.67%). The entropy loss of polymer conformation could not be offset by adsorption energy, leading to its exclusion from the interface and depletion attractive forces. Slurry movement shifted from inter-particle motion to high-molecular-weight polymer sliding in interstitial fluid, forming a lubrication effect. With further PAM content no less than 0.67%, the polymer solution reached a critical entanglement concentration, and the contact of the rotation radius of the long-chain molecules led to entanglement domination. By introducing bridging adsorption, depletion attraction, and entanglement forces, the cohesion of cement-based polymer suspensions was subsequently determined. The results showed a linear correlation between cohesion and PAM concentration raised to powers of 0.30, 1.0, and 0.75 at different interaction stages, and a multiscale validation from microscopic flocculation mechanisms to macroscopic performance was finally completed through a comparative analysis with macroscopic anti-washout performance.