Proactive control model for safety prediction in tailing dam management: Applying graph depth learning optimization

Abstract

Accurate and rapid prediction of monitoring parameters is an important means of proactively preventing safety accidents in tailings dams. Traditional monitoring model uses a single-point time-domain prediction method through feature selection, ignoring the correlation between monitoring point data. Multiple raw monitoring time series were used as direct input to the GCN-AGRU prediction model to estimate response changes in tailings dam operations. Firstly, the spatial location map of sensors in the tailings dam monitoring system was constructed to describe the sensor data in a multi-point arrangement. Then a graph neural network was used to capture the complex spatial dependencies of the sensor location map to obtain the overall safety level of the tailings dam. Secondly, the spatial features extracted from the graph convolutional neural network at different moments were fused with time series and input into a gated recurrent unit (GRU). The purpose was to use the fused features to capture the spatio-temporal correlation between time series of different monitoring locations. Finally, the temporal attention mechanism was combined to predict the dam monitoring data. Based on real data, the algorithm was compared with other algorithms to verify its accuracy and generalizability, which indicates that the model has great significance for improving the risk prevention and control of tailings dams.