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

Rock classification method based on laser induced breakdown spectrum

A laser-induced breakdown and classification method technology, applied in the field of laser spectrum analysis technology and convolutional neural network, can solve the problems of difficult recognition and failure to achieve classification accuracy, achieve strong generalization ability, improve classification accuracy, Reduce the effect of adverse effects

Inactive Publication Date: 2019-07-05
SICHUAN UNIV +1
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the many types of elements contained in rock samples, identification is also very difficult, and the existing traditional pattern recognition methods cannot meet the classification accuracy requirements.

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
  • Rock classification method based on laser induced breakdown spectrum
  • Rock classification method based on laser induced breakdown spectrum
  • Rock classification method based on laser induced breakdown spectrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A rock classification method based on laser-induced breakdown spectroscopy, which uses spectral images as input for the first time, and realizes fast and accurate classification and identification of rock samples through convolutional neural network combined with laser-induced breakdown spectroscopy technology, thereby improving the geological exploration site. Work efficiency has great practical significance for mud logging, drilling and other work, including the following steps:

[0049] 1) making a rock sample; preferably, the rock debris is ground to a powder and then made into a flake sample;

[0050] 2) The spectral images of the rock samples were collected with a laser-induced breakdown spectroscopy device, and the obtained spectral images were divided into three sets of data sets after image preprocessing;

[0051] 3) The convolutional neural network model is established by using the data set composed of spectral images as the input, and the convolutional neural...

Embodiment 2

[0053] The present embodiment is further optimized on the basis of the above-described embodiments, and further to better realize the present invention, the following setting mode is adopted in particular: the step 1) includes the following specific steps:

[0054] 1.1) Place rock debris in an agate mortar and grind to powder;

[0055] 1.2) The powdered rock is supported under a pressure of 6-20 MPa to support a sheet-shaped rock sample; preferably, 2.0 g of ground rock powder is weighed and made into a sheet under a pressure of 8 MPa.

Embodiment 3

[0057] This embodiment is further optimized on the basis of any of the above-mentioned embodiments. Further, in order to better realize the present invention, the following setting mode is adopted in particular: said step 2) includes the following specific steps:

[0058] 2.1) Use a laser-induced breakdown spectroscopy device to collect laser-induced breakdown spectroscopy images of different types of rock samples at multiple different measurement locations, the collection band is 180nm to 580nm, and each sampling location accumulates more than 2 pulsed lasers; preferably , each sampling site (site) accumulates 4 pulse lasers;

[0059] 2.2) Image preprocessing: Grayscale and normalize the laser-induced breakdown spectrum images collected from rock samples;

[0060] 2.3) The laser-induced breakdown spectrum images after grayscale and normalization processing are divided into three sets of data sets: training set, cross-validation set and test set, and the three sets of data set...

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 rock classification method based on a laser induced breakdown spectrum. The method comprises the steps that 1) a rock sample is prepared; 2) a laser induced breakdown spectrum device is used to collect a spectral image of the rock sample, and the acquired spectral image is pre-processed and divided into three data sets; and 3) the data sets composed of the spectral imageare used as an input end to establish a convolutional neural network model, and the convolutional neural network model is optimized and tested; a convolutional neural network based on spectral image recognition is combined with a laser induced breakdown spectrum technology to realize accurate classification of rock samples.

Description

technical field [0001] The present invention relates to the fields of laser spectrum analysis technology, convolutional neural network technology, etc., specifically, a rock classification method based on laser-induced breakdown spectrum. Background technique [0002] Laser-Induced Breakdown Spectroscopy (LIBS) is an atomic emission spectroscopic analysis method that uses high-energy laser pulses to directly focus on the sample, thereby inducing the sample to generate plasma. It is based on the interaction between laser and matter, from A new analytical technique for the analysis of material composition and content in physics and spectroscopy. The development of LIBS technology is very rapid. Due to its advantages of remote detection, multi-element analysis, in-situ measurement, rapidity and no need for complicated sample pretreatment, it makes up for the shortcomings of traditional elemental analysis methods and has obvious advantages in many application fields. In recent ...

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): G01N21/71G06K9/62
CPCG01N21/718G06F18/241G06F18/214
Inventor 段忆翔陈君玺
Owner SICHUAN UNIV
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