Shield tunneling machine soil cabin pressure space distribution prediction method based on deep learning

• Main Authors: GONG YANGKAI, ZHU MINXIANG, CHENG HONGZHAN, REN YUHAO, GENG ZIHENG, CHEN RENPENG, ZHANG CHAO, DENG PENG
• Format: Patent
• Language: Chinese; English
• Published: 05.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER,MECHANICAL EFFICIENCY, OR FLUID PRESSURE; PHYSICS; TESTING

The invention provides a shield tunneling machine soil cabin pressure space distribution prediction method based on deep learning, and the method comprises the following steps: constructing a soil cabin pressure space distribution characteristic function: collecting construction parameters and geological parameters in a shield tunneling process, and forming a data set; constructing a CNN-GRU hybrid model, taking the data set as the input of the CNN-GRU hybrid model, extracting feature vectors of construction parameters and geological parameters at past moments through the CNN model, capturing the relevance of the soil cabin pressure at past time scales through the GRU model, and enabling the output results of the CNN model and the GRU model to pass through a third series layer, then, jointly taking construction parameters and geological parameters at the current moment as input, and outputting a prediction coefficient of a soil cabin pressure spatial distribution characteristic function after passing through