Deep learning-based prediction method for chamber pressure field in shield machines

The chamber pressure is a key factor in the core issues of the stress state of equipment and the stability of tunnel face during shield tunneling. It exhibits significant spatial variability, and its formation and evolution originate from the complex coupling effects of geotechnics and mechanism, which is related to multiple parameters such as geological features and tunnelling parameters. Yet, the spatial distribution features or geological features are generally ignored in the existing methods for predicting the chamber pressure. To probe this problem, a method to predict the chamber pressure field in shield machines is proposed based on the deep learning algorithm guided by the physical feature function of spatial distribution. This method constructs the physical feature function for decoupling the spatial distribution features of the chamber pressure, uses the convolutional neural network and gated recurrent unit to extract the spatial features of the historical information of multi-source parameters and the temporal features of feature coefficient, respectively, and combines the real-time information of multi-source parameters to predict the feature coefficient, so as to realize the prediction of the chamber pressure field. Taking a section of Changsha Metro Line 4 as a case study, this method is used to accurately predict the measured spatial distribution of the chamber pressure with an accuracy of 0.98, which verifies the effectiveness of the proposed method. The sensitivity analysis reveals that the main sensitive parameters of the spatial distribution feature coefficient of the chamber pressure are basically the same in different strata, but their sensitivities vary significantly with the geological conditions of strata. The results may provide guidance for the refined control of the chamber pressure of shield machines in complex strata.