To investigate the failure behavior of composite open-hole plates under tensile loads， a high-precision finite element simulation model is established based on tensile tests of open-hole plates， and a dataset of tensile force-displacement curves is generated in batches. Then， dual long short-term memory （LSTM） neural network models are proposed to predict the force-displacement curve. The first LSTM model is responsible for extracting input features， while the second one directly predicts the force-displacement curve. The research results indicate that this model can efficiently and accurately predict the tensile force-displacement curves of open-hole plates. The coefficient of determination R² on the test set reaches as high as 0.975 5， with the prediction error of key features such as the initial stiffness E₀ being only 1.85% and the prediction error of the maximum load F_max being only 2.16%.