Check patentability & draft patents in minutes with Patsnap Eureka AI!

Geotechnical material discrete element automatic modeling method based on machine learning

A technology of geotechnical materials and machine learning, applied in machine learning, CAD numerical modeling, instruments, etc., can solve problems such as the inability to directly obtain discrete element models, and achieve the effect of rapid modeling

Pending Publication Date: 2021-05-07
NANJING UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The mechanical properties of the discrete element accumulation model are affected by various factors such as particle properties, accumulation process, and cementation, and it is usually impossible to directly obtain the discrete element model with specified mechanical properties

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
  • Geotechnical material discrete element automatic modeling method based on machine learning
  • Geotechnical material discrete element automatic modeling method based on machine learning
  • Geotechnical material discrete element automatic modeling method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings.

[0038] A machine learning-based discrete element automatic modeling method for geotechnical materials, comprising the following steps:

[0039] Step S1, establish a rock discrete element model based on the linear elastic contact theory through MatDEM software. The model is a cuboid with a length of 50mm, a width of 50mm, and a height of 120mm. The model includes an upper pressure plate topPlaten, a sample sample and a lower pressure plate botPlaten stacked in sequence. Apply random velocity and gravity to the model, and then simulate the gravity deposition process to establish a close-packing model; establish a close-packing model through the gravity deposition process.

[0040] Step S2, assigning the macroscopic mechanical properties of sandstone to the compact packing model, and calculating the corresponding micromechanical parameters according to the conversion fo...

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 geotechnical material discrete element automatic modeling method based on machine learning, and the method comprises the steps: firstly building a sandstone geometric model through gravity accumulation operation, then obtaining the actual mechanical properties of the model through a numerical test, generating a sample data set for machine learning training, and carrying out the correlation analysis of the untrained sample data set; according to the sample data, adopting an XGBoost algorithm for training, carrying out correlation analysis on training results, and exploring the relation between the sample size and errors; and finally, carrying out automatic modeling by using the trained XGBoost training model. According to the invention, numerical experiment, training, verification and test operation are carried out on actual mechanical properties, so that rapid modeling of geotechnical materials with specific mechanical properties is realized.

Description

technical field [0001] The invention relates to the technical field of discrete element modeling, and mainly relates to an automatic discrete element modeling method for rock and soil materials based on machine learning. Background technique [0002] Rock and soil mass is relatively continuous macroscopically, but is a systematic structure composed of a series of particles, pores and cracks microscopically. The discrete element method builds a model by stacking and cementing particles, which can naturally simulate the discontinuity and inhomogeneity of rock and soil, and provides an effective method for exploring the microscopic mechanism of the macroscopic mechanical properties of rock and soil. The mechanical properties of the discrete element stacking model are affected by many factors such as particle properties, packing process, and cementation, and it is usually impossible to directly obtain the discrete element model with specified mechanical properties. At present, ...

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): G06F30/27G06F30/23G06N20/00G06F111/10G06F119/14
CPCG06F30/27G06F30/23G06N20/00G06F2119/14G06F2111/10
Inventor 袁冰朱莉莉刘春谢斐夏国庆张宸玮权雪瑞耿焕
Owner NANJING UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com