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

Static penetration test rock stratum intelligent identification method and system, computer equipment and medium

A technology of static penetration and intelligent identification, which is applied to computer components, calculations, calculation models, etc., and can solve problems such as unbalanced sample categories, few types of soil layers, and insufficient research on machine learning technology.

Inactive Publication Date: 2021-02-23
CEEC JIANGSU ELECTRIC POWER DESIGN INST +1
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0026] (1) The discussion of machine learning technology is not comprehensive enough
The current research does not comprehensively discuss the research of machine learning technology in the classification of soil layer based on static penetration test;
[0027] (2) There are few types of soil layers in the current related research
[0028] (3) Domestic relevant research cases are rare
[0031] (1) Existing technology does not fully discuss machine learning technology
The current research does not comprehensively explore the application of machine learning techniques in the classification of soil layers based on CPT
[0032] (2) There are few types of soil layers in the current related research
[0033] (3) Domestic relevant research cases are rare
The rock formation data features obtained through the static penetration test are relatively small (no more than 5), and how to use a small number of features to learn general rock formation category information is very challenging; (3) The sample category is unbalanced

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
  • Static penetration test rock stratum intelligent identification method and system, computer equipment and medium
  • Static penetration test rock stratum intelligent identification method and system, computer equipment and medium
  • Static penetration test rock stratum intelligent identification method and system, computer equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0131]The purpose of the present invention is to provide a comprehensive intelligent soil layer classification technology based on machine learning for the static penetration test, and to provide a new direction for domestic research on soil layer identification in the static penetration test.

[0132] The method of the present invention mainly includes two parts: training machine learning model and using machine learning model, wherein the part of training machine learning model needs to use artificial layered static penetration test data to obtain the soil layer classification model including artificial experience, and use The machine learning model part no longer requires manual participation, and the results of soil layer classification can be obtained by directly putting the original data of the static penetration test into the machine learning model. The block diagram is as Figure 4 As shown, the specific method includes the following steps:

[0133] a. to collect data...

Embodiment 2

[0173] 1. Implementation case

[0174] Implementation case Taking a substation engineering base as the research area, a total of 25 static penetration test drilling points were selected. The relative positions of the 25 points are as follows: image 3shown. Among them, select {1C1, 1C4, 1C5, 1C6, 1S5, 1S7, 1S9, 1S20, 1S22, 1S26, 1S28, 1S29, 1S33, 1S34, 1S35, 1S36, 1S37, 1S39, 1S40, 1S42, 1S44} with a total of 21 points The static penetration test data is the training data set, and the data of four points {1C2, 1C3, 1S43, 1S45} are the test data set. Some sample data are shown in Table 1.

[0175] Table 1 Partial sample data

[0176] Test point depth (m) Cone resistance (MPa) Side wall resistance (MPa) Soil type 0.1 1.13 0.0171 plain fill 2.2 0.47 0.0135 Silty clay (flow molding - soft plastic) 4 0.38 0.0106 Silty clay (flow molding - soft plastic) 5.5 6.33 0.0453 Silt (loose) 13 6.61 0.0697 Silt with silt (medium densit...

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 rock stratum identification, and discloses a static penetration test rock stratum intelligent identification method and system, computer equipment and amedium. The method comprises steps: collecting data; preprocessing the data; dividing a data set; constructing a machine learning model; training a machine learning model; evaluating a classificationmodel; and using the classification model. Soil layer classification of a certain engineering base in China is taken as a research case, application of using a machine learning technology to performsoil layer division in a static sounding test is comprehensively discussed, the types of soil layers in the static sounding test are expanded, an intelligent soil layer classification technology basedon machine learning is provided for the static sounding test, a new direction is provided for research of soil layer identification in a static sounding test in China, the superiority of a machine learning technology in super-multi-class soil layer division based on the static sounding test is verified, and the feasibility of the static sounding test based on the machine learning technology in domestic use is proved.

Description

technical field [0001] The invention belongs to the technical field of rock formation identification, and in particular relates to an intelligent identification method, system, computer equipment and medium for a static penetration test rock formation. Background technique [0002] (1) Research overview of soil layer division based on static penetration test [0003] (1) Basic principles of Cone Penetration Test (CPT) [0004] Static CPT is to use quasi-static force to press a probe equipped with a sensor into the soil at a constant speed. Due to the different softness and hardness of various soils in the formation, the resistance suffered by the probe is naturally different. The sensor will be of this size Different penetration resistances are recorded by inputting electrical signals into the recording instrument, and then the qualitative relationship and statistical correlation between the penetration resistance and the engineering geological characteristics of the soil a...

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): G06K9/62G06N20/00G01N3/42G01N33/24
CPCG06N20/00G01N33/24G01N3/42G01N2203/0019G01N2203/0076G01N2203/0212G06F18/23213G06F18/24155G06F18/2411G06F18/24323G06F18/2415G06F18/214
Inventor 任治军葛海明葛阳颜雪松李铭
Owner CEEC JIANGSU ELECTRIC POWER DESIGN INST
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