The excavation stratum of the earth pressure balance (EPB) shield machine is complex and changeable. For ensuring the excavated interface stabilization, the rotational speed of screw conveyor must be precisely controlled to maintain the balance of earth pressure in sealed cabin and to avoid accidents such as ground collapse or upliftment. A data-driven intelligent optimal model is presented by the paper, which organically integrates the complete ensemble empirical mode decomposition of adaptive noise (CEEMDAN), sparrow search algorithm (SSA) and long short-term memory (LSTM) network to achieve accurate prediction of screw conveyor rotation speed. Firstly, Pearson correlation analysis method is used to analyze the historical data of shield tunneling, and the tunneling parameters strongly related to the change of screw conveyor rotation speed are obtained as model input. Secondly, the CEEMDAN is used to decompose the obtained parameter data set into several modal components, and then the denoised data is reorganized to capture the changing characteristics of the original data and reduce the complexity of the data. Then, the parameters such as the learning rate of the LSTM network are optimized by using the strong global search ability of SSA to enhance the prediction precision further in the model. Finally, based on decomposed and reorganized data, SSA-LSTM is used to establish a rotation speed intelligent prediction model realize precise controlling of screw conveyor rotation speed. The simulation experiment is carried out by using the construction data of a section of Beijing Metro Line 10, and the results of three evaluation indexes of the model are given: Mean Absolute Error (MAE) is 0.02878, Mean Absolute Percentage Error (MAPE) is 0.00882 and R2 is 0.99909, which shows that the model has good prediction performance. The control effect of the method on the earth pressure balance of the sealed cabin is tested, and the maximum error value is 0.25%, which verifies the engineering applicability of the method.