Neural network surrounding rock grading prediction method and system based on geophysical prospecting data

A kind of surrounding rock classification and neural network technology, applied in the field of tunnel surrounding rock identification, can solve the problems of poor timeliness of tunnel surrounding rock, weakening the polysolution of geophysical exploration technology, and large labor cost consumption, so as to weaken the negative impact and reduce human subjective factors. The effect of reducing labor costs

Pending Publication Date: 2021-10-29
新疆建筑科学研究院(有限责任公司)
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Through the above analysis, the existing problems and defects of the existing technology are: great dependence on the experience of engineering and technical personnel, inability to weaken the multiple solutions of geophysical prospecting technology, and high labor cost consumption
[0004] The existing technology has poor timeliness, large fluctuations and low accuracy for advanced prediction of tunnel surrounding rock quality

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
  • Neural network surrounding rock grading prediction method and system based on geophysical prospecting data
  • Neural network surrounding rock grading prediction method and system based on geophysical prospecting data
  • Neural network surrounding rock grading prediction method and system based on geophysical prospecting data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] 1. Use the geological radar (electromagnetic wave) method to forecast ahead of the tunnel face, and arrange two survey lines for each tunnel face ( figure 2 ), to obtain two GPR echo maps ( image 3 , Figure 4 ).

[0055] 2. Use matlab programming to perform wavelet noise reduction processing on the geological radar echo map (the code is as follows) to remove noise.

[0056] I=imread('E:\geological radar picture\exit right hole\K20+504~K20+474 2-5.png');

[0057] [thr,sorh,keepapp]=ddencmp('den','wv',I);

[0058] K=wdencmp('gbl',I,'db45',4,thr,sorh,keepapp);

[0059] K = uint8(K);

[0060] 3. Write a 7-layer fully connected neural network based on TensorFlow. The number of neurons in the input layer is 304440, the second layer is 128, followed by a Dropout layer (neuron inactivation ratio is 50%), the third layer is 64, the fourth layer is 32, the fifth layer is 16, and the There are 8 in the six layers and 3 in the output layer.

[0061] 4. Convert the radar ...

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 belongs to the technical field of tunnel surrounding rock recognition, and discloses a neural network surrounding rock grading prediction method and system based on geophysical prospecting data, and the method comprises the steps: carrying out the advanced prediction of the front of a tunnel face through a geological radar, namely an electromagnetic wave method, and obtaining a geological radar echo map; carrying out wavelet noise reduction processing on the obtained geological radar echo map; obtaining a one-dimensional data matrix based on the geological radar echo map after noise reduction; taking the obtained one-dimensional data matrix as an input value of a full-connection neural network model, taking the surrounding rock grade of the corresponding mileage as a label value, training and predicting the full-connection neural network model, and obtaining an optimal full-connection neural network model; and carrying out surrounding rock grading prediction by using the obtained optimal full-connection neural network model. The tunnel surrounding rock can be effectively graded and identified.

Description

technical field [0001] The invention belongs to the technical field of tunnel surrounding rock identification, in particular to a neural network surrounding rock classification prediction method and system based on geophysical prospecting data. Background technique [0002] At present, during tunnel construction, a large number of geological factors that affect safe production are often encountered, especially the sinister and complex geological conditions that cannot be predicted in advance due to the limitation of detection technology, such as fault structures, sudden changes in rock formations, karst and other water-bearing anomalies body, will be more likely to cause sudden accidents in the tunnel construction process. At present, most advanced geological forecasts use geophysical prospecting technology for tunnel geological forecasting. Because geophysical prospecting technology has multiple solutions, the prediction accuracy is very dependent on the experience of engin...

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): G06Q10/04G06T5/00G06N3/04G06K9/62G06F30/27G06F30/13
CPCG06Q10/04G06T5/002G06F30/13G06F30/27G06T2207/20084G06T2207/20081G06T2207/30108G06N3/045G06F18/214
Inventor 刘学军刘震哈月龙侯宪明蒋国新陈鑫李严君尼加提·努尔太
Owner 新疆建筑科学研究院(有限责任公司)
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap