Shield tunneling line real-time prediction method, terminal and medium

Abstract

The invention provides a shield tunneling line real-time prediction method, a terminal and a medium. The method comprises the following steps: establishing an original parameter set; screening the original parameter set, and performing dimensionless processing to obtain a standardized data set; performing feature extraction on the standardized data set, wherein the feature extraction refers to reducing the correlation among shield operation parameters, geological parameters and tunnel geometric parameters, and establishing a feature parameter set for replacing an original parameter set; and determining a GRU deep learning network, and obtaining a shield tunneling line deviation prediction value by using the GRU deep learning network. According to the invention, through feature extraction, noise in the original parameter data is reduced, correlation in the original parameter data is reduced, the complexity of a deep network model is reduced, and the accuracy of a prediction result is improved.

Description

technical field [0001] The invention belongs to the field of tunnel construction, and in particular relates to a real-time prediction method, a terminal and a medium for a shield excavation line. Background technique [0002] The "Medium and Long-term Railway Network Planning" issued by China Railway Corporation pointed out that the target scale of my country's railway network will reach 200,000 kilometers in 2030, an increase of nearly 33.3% compared to 2020. The shield tunneling method is one of the main construction methods for urban subway construction. During the shield construction process, it is necessary to excavate according to the tunnel design axis. Due to the influence of construction personnel experience, geological conditions, tool wear and other factors, the actual excavation route of the shield often deviates from the design axis. In the construction of complex strata such as upper soft and lower hard, the cutter head of the shield machine is affected by unb...

AI Technical Summary

Problems solved by technology

This method overcomes the shortcomings of the existing methods that do not consider the influence of the shield operating parameters on the line deviation at the adjacent time during the excavation process and the inability to predict in real time, realizes the real-time prediction of the line deviation of the shield tunneling, and improves the accuracy and accuracy of the prediction results. reliability

Images