Intelligent real-time prediction for shield machine position on the basis of BWO-LSTM-GRU

Abstract Due to the complexity and variability of shield machine working environment, it is very important to accurately control and regulate the position trajectory of shield machine. For that reason, an intelligent real-time prediction model of shield machine position based on BWO-LSTM-GRU (Beluga whale optimization-Long Short-term Memory-Gated recurrent unit) is proposed in this paper. Firstly, the real-time data of shield machine are processed based on Pearson correlation analysis, and the tunneling parameters presenting medium-strong correlation with the position parameters are filtered to obtain, which were used to be input variables for prediction models. Secondly, LSTM-GRU position prediction model was established separately for shield machine position parameters, and four hyperparameters of the model were optimized separately using BWO. Finally, BWO-LSTM-GRU position prediction models are used to realize the intelligent real-time prediction of the motion trajectories at four positions for shield machine. The simulation results indicate that the prediction deviation in the position prediction model is within 3 mm, and it can accurately complete the task of real-time prediction, providing real-time data support for shield machine drivers.