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

Clastic rock mineral composition recognition method, lithology naming method and related devices

A technology of mineral composition and identification method, which is applied in the fields of information technology and reservoir evaluation, can solve the problems of high impact on identification results, time-consuming identification of mineral composition, and inability to achieve accurate quantification, so as to avoid dependence on professional technicians and realize specific Quantification, fast and efficient automatic recognition effect

Pending Publication Date: 2021-11-09
PETROCHINA CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional mineral composition identification method of clastic rock thin slices relies on professionals to observe and estimate visually under an optical microscope, which often takes a lot of time, resulting in time-consuming and laborious identification of mineral components, and relies heavily on professionals, and the identification results are affected. Highly influenced by subjective factors, accurate quantification cannot be achieved

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
  • Clastic rock mineral composition recognition method, lithology naming method and related devices
  • Clastic rock mineral composition recognition method, lithology naming method and related devices
  • Clastic rock mineral composition recognition method, lithology naming method and related devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Embodiment 1 of the present invention provides a method for identifying mineral components of clastic rocks, the process of which is as follows figure 1 shown, including the following steps:

[0050] Step S11: using the instance segmentation model to segment and extract the image units corresponding to the mineral particles from the multiple images of the thin slice with different light sources.

[0051] Generally, it is necessary to combine the characteristic morphology under single polarized light and crossed polarized light at multiple angles to accurately identify mineral particles. A plurality of different light source images of the above-mentioned flakes, which may include the following images of the flakes:

[0052] Single polarized images, crossed polarized images at angles of 0°, 15°, 30°, 45°, 60° and 75°.

[0053] The angle selection of the above-mentioned crossed polarization is obtained through the analysis of a large number of experimental data, which ca...

Embodiment 2

[0073] Embodiment 2 of the present invention provides a clastic rock lithology naming method, including identifying the type of mineral grains in the thin section through the above-mentioned clastic rock mineral composition identification method; naming according to the setting according to the total area of ​​each type of mineral grains Rules determine the lithological designation of thin sections. refer to Figure 5 As shown, its specific implementation process includes the following steps:

[0074] Step S51: Identify the type of mineral grains in the flakes.

[0075] For the specific identification process, refer to the description in Embodiment 1, which will not be repeated here.

[0076] Step S52: Determine the equivalent diameter of the mineral particles.

[0077] In the identification process of mineral particle type, the image unit corresponding to the mineral particle has been segmented and extracted from multiple different light source images of the thin slice, th...

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 clastic rock mineral composition recognition method, a lithology naming method and related devices. The clastic rock mineral composition recognition method comprises the following steps: respectively segmenting and extracting image units corresponding to mineral particles from a plurality of different light source images of a slice through an instance segmentation model; utilizing a convolutional neural network model to obtain pooling features of the image units; for all the image units with the same position information, according to the corresponding relation between the light source types and the weights, the pooling features of the image units and the light source types of the images to which the image units belong, determining the fusion features of all the image units; and inputting the fusion features into a time recurrent neural network model, and determining the type of the corresponding mineral particles according to an output result. The mineral components can be quickly, efficiently and automatically recognized, and the recognition accuracy is high.

Description

technical field [0001] The invention relates to the technical fields of information technology and reservoir evaluation, in particular to a clastic rock mineral composition identification method, a lithology naming method and related devices. Background technique [0002] Rock mineral composition contains rich geological information, and mineral composition identification is the core content of clastic rock thin section identification. The results of mineral composition identification can not only provide relevant data information and basis for the study of mineral formation environment, rock genesis, formation history and formation conditions, and the correlation between different rocks; at the same time, it can provide a basis for rock naming. Therefore, the identification of mineral composition has important practical significance. Doing a good job in the identification of mineral composition can better apply the clastic rock thin section data to practice and provide guid...

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): G06T7/00G06T7/10G06T7/62G06K9/62G06N3/04G06N3/08
CPCG06T7/0002G06T7/10G06T7/62G06N3/049G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06N3/045G06F18/2431G06F18/253
Inventor 李欣任义丽吴健平胡延旭李彬罗路陶治罗嗣梧崔京钢郭永军李长新
Owner PETROCHINA CO LTD
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