Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Tunnel surrounding rock pressure prediction method for slurry balance shield, equipment and storage medium

A technology of surrounding rock pressure and mud-water balance, applied in neural learning methods, neural architecture, design optimization/simulation, etc., can solve problems such as surface collapse, noise tunnel face pressure fluctuation, and excavation face mud pressure prediction, etc. Predicting and reducing the probability of construction accidents and subsequent use of tunnels, and the effect of eliminating noise interference

Pending Publication Date: 2021-11-12
GUANGZHOU UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, it is often disturbed by blockage, causing noise and large fluctuations in the pressure of the tunnel face, which makes it difficult to predict the pressure of the excavation face mud, resulting in a series of accidents such as surface subsidence.

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
  • Tunnel surrounding rock pressure prediction method for slurry balance shield, equipment and storage medium
  • Tunnel surrounding rock pressure prediction method for slurry balance shield, equipment and storage medium
  • Tunnel surrounding rock pressure prediction method for slurry balance shield, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Example 1 illustrates a flowchart of a proposed method for predicting highly fluctuating tunnel parameters. refer to figure 1 , S represents the time series of PLC data in a ring. First, the denoising method based on VMD-DFA (Variational Mode Decomposition-Detrended Fluctuation Analysis) is used to obtain the denoising signal of the PLC data time series. BLIMFs (Band-limited Intrinsic ModeFunctions, intrinsic mode components of limited bandwidth) are expressed as u1, u2,...uk,uk+1,...uk_optimal. u1, u2, ... uk are considered as denoised signals, the parameter k is determined by the scaling exponent, and other components of BLIMFs are considered as noise. The determination of K_optimal will be given in the next embodiment. Cross-correlation analysis (Canonical Correlation Analysis, CCA) is performed on the denoised signal to distinguish the trend component and the fluctuation component. Two predictors based on the strength and fluctuation of LSTM (Long Short-Term Mem...

Embodiment 2

[0048] Example 2 describes how the denoising method works. Regarding the variational mode decomposition (VMD) part: the VMD algorithm is used to decompose the PLC data time series S(t) in the ring into discrete mode numbers uk, k=1, 2, ... K_optimal. Each uk mode has a narrowband center frequency wk. In order to determine uk and wk, the VMD algorithm needs to solve the constrained variational problem (formula (1)):

[0049]

[0050] where t is the time script, δ is the Dirac function, and * denotes convolution. {uk} and {wk} denote the obtained modes and center frequencies, respectively. Application of the quadratic penalty α and the Lagrangian multiplier λ transforms Equation (1) into Equation (2):

[0051]

[0052] Equation (2) can be solved by the Alternating Direction Method of Multipliers (ADMMs) of the multiplier algorithm. The solution can be expressed as equation (3).

[0053]

[0054] This problem can be solved in the frequency domain with the help of th...

Embodiment 3

[0067] Example 3 describes a PLC data prediction model based on coupled CCA-LSTM. About CCA: Cross-correlation analysis (CCA) is used to study the relationship between denoised PLC data and its decomposed components. The cross-correlation function and uj of noisy time series, 1≤j≤k, are defined as formula (11):

[0068]

[0069] Sdenoised and uj are the mean values ​​of each time series, and N is the length of the time series. T is the time log, indicating that the feature that was noisy at time T appears in uj at time t+T. Based on δj, PLC data after denoising, S trend and S denoised The trend and volatility components will be determined.

[0070] About LTSM: As a recurrent neural network (RNN), LSTM network uses a gate mechanism to overcome the vanishing gradient problem caused by the recursive structure of RNN. figure 2 The detailed structure of the gate is shown. The forward calculation method is shown in formula group (13). Three gates are used in the LSTM unit...

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 tunnel surrounding rock pressure prediction method for a slurry balance shield, equipment and a storage medium. The method comprises the following steps: acquiring tunnel parameters and geological data, and sorting the tunnel parameters and the geological data into time sequence data; separating the time sequence data; predicting a separated first component and a separated second component; and summing a first prediction result and a second prediction result, and outputting the sum as a prediction result. According to the invention, noise of a excavation face can be correspondingly eliminated according to needs. The invention is applied to the technical field of underground engineering construction. According to the invention, by means of a mature deep learning model, when shield is carried out under the mudstone-containing mixed stratum condition, pressure of tunnel surrounding rock can be reasonably predicted, corresponding risks in the construction process are avoided, and the accident rate is reduced; and in the aspect of academic research, technicians in the field can further research and optimize surrounding rock pressure prediction conveniently.

Description

technical field [0001] The invention relates to the technical field of underground engineering construction, in particular to a tunnel surrounding rock pressure prediction method, equipment and storage medium for mud-water balance shield tunneling. Background technique [0002] Shield tunneling is a key link in the construction of underground tunnels. Shields are classified according to the principle of balanced excavation face pressure, which can be divided into mud-water balance shields, earth pressure balance shields and air pressure balance shields. Among them, the mud-water balance shield is suitable for mixed bottom conditions containing mudstone. However, in practical applications, it is often disturbed by blockage, resulting in large fluctuations in noise and tunnel face pressure, which makes it difficult to predict the pressure of the excavation face mud, resulting in a series of accidents such as surface subsidence. In order to reduce the risk of construction acc...

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): G06F30/13G06F30/27G06N3/04G06N3/08G06F119/14
CPCG06F30/13G06F30/27G06N3/084G06F2119/14G06N3/044
Inventor 蔡长青
Owner GUANGZHOU UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com