Super-large shield section frozen soil body temperature characteristic optimization method based on Gaussian process machine learning and device thereof

A machine learning and Gaussian process technology, applied in earth-moving drilling, design optimization/simulation, mining equipment, etc., can solve the problems of large flowing water in sandy soil, waste of resources, poor economy, etc., to strengthen environmental protection and reduce resources The effect of waste and cost reduction

Pending Publication Date: 2021-10-19
CENT & SOUTHERN CHINA MUNICIPAL ENG DESIGN & RES INST
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] see figure 1 , the freezing reinforcement of the existing shield working wells is often determined according to the specifications, and at the same time, the reinforcement is frozen. The freezing requires that the active freezing temperature is generally -28°C, and the temperature of the freezing body is generally -8°C to -10°C, and it needs to be maintained. Freezing prevents the temperature from being lost due to the influence of the external temperature, which affects the effective thickness of the frozen body
In order to meet the safety of the starting of the sea-crossing tunnel, it is required that the active freezing should be carried out continuously under the condition of satisfying the effective thickness of the frozen body until the starting of the shield tunnel ends. This method will cause unnecessary waste of resources, and the water flow of the seaside environment Strong, when the characteristics of temperature attenuation cannot be judged, it is necessary to use a large amount of refrigerant to maintain the effective thickness of the frozen body
[0005] In the past, the design and construction of the freezing method were relatively extensive, and this method could not effectively control its adverse impact on the surrounding environment. The extensive design and construction often had the characteristics of poor economy and poor feasibility. Take the shield tunnel as an example. The horizontal freezing design requires a width of 3m and two rows of freezing pipes. However, there is a row of freezing pipes located in the shield excavation surface, which needs to be pulled out when the tunnel is broken. Fast, there is no guarantee that the 3m width of the frozen body can meet the requirements when the shield starts, and it will cause too much waste of resources

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Super-large shield section frozen soil body temperature characteristic optimization method based on Gaussian process machine learning and device thereof
  • Super-large shield section frozen soil body temperature characteristic optimization method based on Gaussian process machine learning and device thereof
  • Super-large shield section frozen soil body temperature characteristic optimization method based on Gaussian process machine learning and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments, but these embodiments should not be construed as limiting the present invention.

[0024] figure 1 The described technical content has been described in detail in the background art, and will not be repeated here.

[0025] see figure 2 , the present invention is based on the Gaussian process machine learning method for optimizing the temperature characteristics of the super-large shield section frozen soil, including the following steps:

[0026] S1. Carry out the construction of freezing tubes and temperature measuring tubes, and implement freezing, and monitor the initial temperature values ​​of 19 temperature measuring tubes;

[0027] S2. Implement active freezing, and collect the values ​​of each measuring point multiple times;

[0028] S3, according to the temperature t monitored by the temperature measuring tubes of the existing 19 poi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a super-large shield section frozen soil body temperature characteristic optimization method based on Gaussian process machine learning, and the method comprises the following steps: S1, carrying out the fitting of a temperature function of a reinforced soil body through the Gaussian process machine learning, and obtaining a function rule of the temperature; and S2, performing particle swarm intelligent optimization on the obtained implicit function, and obtaining the frozen surface of the frozen body. The invention also discloses a super-large shield section frozen soil body temperature characteristic optimization device based on Gaussian process machine learning, and the device comprises a temperature function fitting module which carries out the fitting of a temperature function of a reinforced soil body through the Gaussian process machine learning, and obtains a function rule of the temperature; and a frozen body function fitting module which is used for carrying out particle swarm intelligent optimization on the obtained implicit function and obtaining a frozen surface of the frozen body. The method can be widely applied to the technical field of tunnels and underground engineering by effectively controlling the time length of positive freezing, intelligently optimizing freezing, reducing resource waste and enhancing environmental protection.

Description

technical field [0001] The invention relates to the technical field of tunnels and underground engineering, in particular to a method and device for optimizing the temperature characteristics of frozen soil with a super-large shield section based on Gaussian process machine learning. Background technique [0002] The freezing method is a method that uses artificial refrigeration to temporarily freeze the reinforced formation and cut off the effect of groundwater. At present, the freezing method is mostly used in the origination and reception of shield tunneling wells, especially when there is a permeable layer on the shield tunneling surface Time. The freezing method construction can effectively cut off the starting and receiving portals and the soil of the permeable layer, and can better ensure that the shield tunneling wells will have water gushing and soil gushing caused by the pressurized water carried by the permeable layer at the tunnel opening when the shield tunnelin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F30/25G06F30/27E21D9/00
CPCG06F30/25G06F30/27E21D9/001
Inventor 刘华何小龙张庆何振华张美聪桑中顺岳龙杨明
Owner CENT & SOUTHERN CHINA MUNICIPAL ENG DESIGN & RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products