Real-time prediction method and system for shield tunneling machine cutterhead torque

A technology of cutter head torque and real-time prediction, applied in instrument, geometric CAD, design optimization/simulation, etc., can solve problems such as endangering personal safety, safety accidents, economic losses, etc.

Pending Publication Date: 2021-02-09
SHANGHAI JIAO TONG UNIV +1
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

During the construction process of the shield machine, the cutterhead system is extremely easy to be stuck and damaged, which will affect the construction period and may even cause safety accidents, causing major economic losses and endangering personal safety

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
  • Real-time prediction method and system for shield tunneling machine cutterhead torque
  • Real-time prediction method and system for shield tunneling machine cutterhead torque
  • Real-time prediction method and system for shield tunneling machine cutterhead torque

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] Aiming at the problems of low prediction accuracy and weak generalization ability existing in the current cutterhead torque prediction method, the present invention provides a real-time cutterhead torque prediction method based on residual CNN-LSTM neural network.

[0088] A method for real-time prediction of cutter head torque of a shield machine according to the present invention includes:

[0089] Step M1: Select the operating parameters of the shield machine that affect the torque of the cutter head during the actual working process of the shield machine and meet the preset requirements; including jack propulsion speed, geological pressure on the shield machine, cutter head thrust, cutter head speed, shield machine The force of the engine propulsion system, the current and frequency of the propulsion motor, etc.

[0090] Step M2: Preprocessing the operating parameters of the shield machine that meet the preset requirements;

[0091] Step M3: Based on the CNN neural...

Embodiment 2

[0171] Embodiment 2 is a modification of embodiment 1

[0172] The present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0173] refer to Figure 1 to Figure 9 , a method for real-time prediction of cutter head torque based on residual CNN-LSTM neural network, including the following steps:

[0174] Step 1: Select the key parameters, and select the operating parameters of the shield machine that have a greater impact on the cutter head torque during the actual working process of the shield machine as the input of the prediction model. figure 1 It is the database diagram of the operating parameters of the actual construction of the shield machine, figure 2 It is the cosine similarity diagram between the operating parameters of the shield machine and the cutter head torque in the database, and the operating parameters of the shield machine whose cosine similarity with the cutter head torque is greater than 0.85 an...

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 provides a real-time prediction method and system for a shield tunneling machine cutterhead torque, and the method comprises the steps: selecting shield tunneling machine operation parameters with the impact on the cutterhead torque meeting a preset requirement in an actual working process of a shield tunneling machine, and carrying out the preprocessing; constructing a residual CNN-LSTM neural network cutterhead torque prediction model based on the CNN neural network, the residual network and the LSTM neural network by utilizing a keras packet under a Tensorflow framework; training the residual CNN-LSTM neural network cutterhead torque prediction model; selecting shield tunneling machine operation parameter data at a preset moment, and predicting a cutterhead torque value ata next moment by utilizing the trained residual CNN-LSTM neural network cutterhead torque prediction model; and respectively calculating a mean square error, an average absolute error and an averageabsolute percentage error, and testing the prediction precision of the torque of the cutterhead. According to the method, high-precision prediction of the cutterhead torque of the shield tunneling machine is achieved, and the automation and intelligence level of the shield tunneling machine can be improved.

Description

technical field [0001] The present invention relates to the field of tunneling parameter prediction and control parameter optimization in the construction process of a shield machine, in particular to a method and system for real-time prediction of cutterhead torque of a shield machine, and more specifically to a method and system based on residual CNN-LSTM Real-time prediction method of shield machine cutterhead torque based on neural network. Background technique [0002] The full name of the shield machine is the tunnel boring machine, which is widely used in the tunnel construction of high-speed railways and subways. Compared with the traditional blasting method, the tunnel excavation using the shield machine is more efficient, safe and environmentally friendly. In the future, more railways will be built in our country, and shield machines will be more widely used by then. During the construction process of the shield machine, the cutter head system is extremely easy to...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/17G06F30/27G06F119/14
CPCG06F30/17G06F30/27G06F2119/14
Inventor 刘成良陶建峰余宏淦覃程锦石岗雷军波毛帅孙浩
Owner SHANGHAI JIAO TONG UNIV
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