The model based on autoencoder performs poorly in identifying anomalies in concrete dam measured data, and existing methods struggle to accurately detect minor abnormal values in time series. This paper constructs a novel unsupervised anomaly detection model that integrates long short-term memory network (LSTM), multi-head attention mechanism (MA), and generative adversarial network (GAN) into memory-augmented deep autoencoder (MemAE) model, namely the multi-head attention LSTM- memory-augmented deep autoencoder- generative adversarial network (MALSTM-MemAE-GAN). This model takes MemAE as the core, replaces the encoder part with LSTM to extract hidden features dependent on time series, and then uses MA to enhance the model’s focusing ability on minor abnormal values after the memory-augmented module. GAN is introduced to make the reconstructed data closer to the real samples. Taking the displacement and crack data of a concrete dam as an example, two experimental datasets are established (The abnormal intensity of the second experimental datasets is halved on the basis of the first experimental datasets). Using a multi-metrics evaluation system centered on the F1 score, ablation and comparative experiments are conducted on the proposed MALSTM-MemAE-GAN model. Dynamic detection is achieved through a sliding window approach. Results demonstrate average F1 scores of 0.9756 and 0.9435 for static detection across two experimental datasets, validating the model’s robust performance and accurate detection capability for minor abnormal values. Furthermore, the model enables dynamic detection of dam measured data with excellent results. This paper provides scientific basis and technical support for the dam structural health monitoring.

Influenced by many factors such as material performance attenuation, structural defect repair, and reinforcement, the structural reliability of a gravity dam changes in different periods, which are called dynamic effects. Traditional methods are inclined to calculate and analyze the structural probability reliability from the random or fuzzy uncertain characteristics of parameters. However, in practice, it is difficult to obtain the probability distribution of uncertain parameters as well as the performance function, which is too nonlinear to be expressed. In addition, gravity dam failures are low probability events. Thus, a reliability calculation model and method for the gravity dam system considering dynamic effects under the practice of reinforcement are studied by integrating the theory of interval mathematics and nonprobability reliability. First, with the help of the monitoring data, and physical model and numerical simulation results of the gravity dam before and after the reinforcement, we establish a nonprobabilistic reliability (N-PR) calculation model for the gravity dam element and system based on the bounds of uncertain parameters and propose an inversion method for the bounds of uncertain parameters. Subsequently, by combining the response surface method with the central composite design technique, an N-PR index calculation method for gravity dams considering dynamic effects is developed. It turns out that the given model and method can effectively pave the way to avoid falling into the limitations of classical probabilistic reliability analysis of which the uncertain parameters require to be randomly changed and the results are highly sensitive to the parameters. In addition, it can better adapt to the characteristic of gravity dam performance function, which is too nonlinear to be expressed explicitly. When employing this method to analyze the reliability of gravity dam services, we are able to evaluate and predict the changing process and the trend of it more objectively, and have a closer look at the comprehensive influence and contribution of reinforcement to dam service reliability.