Concrete Dam Deformation Prediction Model Research Based on SSA–LSTM

In the context of dam deformation monitoring, prediction task is essentially a time series problem that involves non-stationarity and complex influencing factors. To enhance accuracy predictions address challenges posed by high randomness parameter selection in LSTM models, novel approach called sparrow search algorithm–long short-term memory (SSA–LSTM) has been proposed for predicting concrete dams. SSA–LSTM combines SSA optimization algorithm with to automatically optimize model’s parameters, thereby enhancing performance. Firstly, was used as an example preprocess historical monitoring data cleaning, normalizing, denoising, due specificity structure, multi-level denoising abnormal performed. Second, some were train model, hyperparameters long neural network model (LSTM) optimized better match input structure. Finally, high-precision carried out. The this study significantly improves forecasting demonstrates effectiveness long-term prediction. provides reliable efficient evaluating stability structures, offering valuable insights engineering practices decision-making.