Roadway surrounding rock deformation predicting method based on neural network

A technology of neural network and surrounding rock deformation, applied in biological neural network models, special data processing applications, instruments, etc., can solve problems such as the maximum plastic zone damage depth, and achieve the effect of improving calculation efficiency

Inactive Publication Date: 2016-01-20
CHINA UNIV OF MINING & TECH
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Technical problem: The purpose of this invention is to propose a method for predicting the deformation of the surrounding rock of the roadway using a neural network to solve the problem of predicting the subsidence of the roof of the surrounding rock of the roadway, the displacement of the bottom plate, the displacement of the side of the roadway and the damage depth of the maximum plastic zone. question

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
  • Roadway surrounding rock deformation predicting method based on neural network
  • Roadway surrounding rock deformation predicting method based on neural network
  • Roadway surrounding rock deformation predicting method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In this prediction method, the key influencing factors of the surrounding rock are obtained through hierarchical analysis, the BP neural network model is established, and the training samples formed by the data groups obtained from the previous monitoring under different geological conditions are input. The data structure is a multidimensional matrix, and the training sample data is passed through trainlm The function trains the neural network system; the trained neural network is used to predict the initial deformation of the roadway excavation, and according to the input index parameters, the settlement of the surrounding rock roof, the displacement of the bottom plate, the displacement of the side of the roadway and the generated The maximum damage depth in the plastic zone, the neural network will predict the roadway deformation at the initial stage of excavation according to the prediction request, select appropriate support parameters to control the roadway support,...

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 roadway surrounding rock deformation predicting method based on a neural network and belongs to the method for predicting roadway surrounding rock deformation. Key influence factors of surrounding rock are obtained by means of layer analysis, site detection data under different geological conditions are collected and arranged, reliable data arrays obtained through monitoring serve as a training sample of the roadway surrounding rock deformation, the data of the training sample train the network system through trainlm functions, and a BP neural network model can be set up; the trained neural network is utilized for predicting the deformation amount at the initial excavation stage of a roadway, deflection of a surrounding rock top plate, moving-up amount of a bottom plate, displacement of roadway walls and generated maximum plastic zone damage depth are obtained according to input index parameters, the neural network predicts the roadway deformation of the initial excavation stage according to the prediction request, proper support parameters are selected for controlling support of the roadway, and safety accidents caused by instability of the rock are prevented. The reliable prediction data are provided for the roadway exploration and excavation processes to instruct the construction process of the roadway, and working procedures are arranged reasonably.

Description

technical field [0001] The invention relates to a method for predicting the deformation of the surrounding rock of the roadway, in particular to a method for predicting the deformation of the surrounding rock of the roadway by using a neural network. technical background [0002] With the rapid development of our country's social economy, the development and utilization of underground resources have become more and more extensive. For underground mining projects, in order to ensure the safe production of the mine, the first problem to be solved is how to maintain the stability of the surrounding rock of the roadway after excavation and unloading, and the research on the stability of the surrounding rock of the underground roadway caused by this It has also received increasing attention and attention from people. More and more studies have found that the instability and failure of the surrounding rock of the roadway is often caused by the stress overload or excessive displac...

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): G06F17/50G06N3/02
Inventor 赵玉成黄丽魏锋李冲杨卫明王朋李二霞
Owner CHINA UNIV OF MINING & TECH
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