Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic Generation Method of Training Images of Composite Turbidity Channels

A technology for training images and automatic generation, applied in image data processing, instruments, calculations, etc., can solve problems such as lack of targeted methods, and achieve the effect of reducing difficulty

Active Publication Date: 2021-05-07
YANGTZE UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although many scholars have studied turbidite channels and generated corresponding training images, few scholars have studied the generation of training images of composite turbidite channels. Many problems, such as: the evolution of a single turbidite channel In the process of forming a complex channel, how to migrate along the paleocurrent direction as a whole, how to accumulate vertically, and how to restrict the evolution degree of a single channel, etc., there is still no targeted method

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
  • Automatic Generation Method of Training Images of Composite Turbidity Channels
  • Automatic Generation Method of Training Images of Composite Turbidity Channels
  • Automatic Generation Method of Training Images of Composite Turbidity Channels

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] 1. According to the actual situation of the work area, the grid division of the training image is determined to be 120×200×36, the number of original grid points is 3,200,000, and the grid size is 3(m)×3(m)×0.5(m). Among them, a single turbidity channel passes through the entire work area, with a depth of 3 meters to 10 meters, with an average of 5 meters, a width of 30 meters to 200 meters, with an average of 75 meters, and a width-to-depth ratio between 10 and 40, with an average of 5 meters. 15, the curvature ranges from 1.0 to 5.4, with an average of 1.9.

[0089] 2. Take the value within the range of the existing measurement data, take the maximum depth of a single channel as 5 meters, the width-to-depth ratio as 13 meters, the initial curvature as 1.30, and the theoretical curvature as K t is 1.90, and the main direction of a single channel is 180°. The evolution probability of the channel centerline for the overall migration along the paleocurrent is 0.1; the ev...

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 automatic generation method of the training image of the composite turbidity channel of the present invention, the method includes the evolution of the centerline of the channel; after each evolution of the centerline of the channel, the curvature of the current channel and the theoretical curvature are compared, if the curvature of the current period is less than the theoretical curvature, then Continue to the next channel centerline evolution. If the current channel curvature is greater than or equal to the theoretical curvature, the evolution degree of the composite turbidite channel is determined by the closeness of the current period curvature and the previous period curvature to the theoretical curvature. The method for automatically generating the training image of the compound turbidite channel in the present invention can quickly combine the investigation results of the research area with the statistical data of the geological database, and transform it into a training image for industrial digitization.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration and development, in particular to a method for automatically generating training images of composite turbidite channels. Background technique [0002] Turbidite channel is an important part of deep water fan, and it is also a very complex and highly valued reservoir in the process of deep water oil and gas exploration, evaluation and development. Regarding the division of turbidite channel system configuration, there is no unified scheme at home and abroad. At present, the 7-level configuration unit division scheme of Lin Yu (2013) is widely used, mainly from single channel, composite channel and channel system 3 Study on the sedimentation model of turbidite channels at different levels. Bu Fanqing et al. (2013) used the partition method to simulate two sets of sedimentary systems with different provenances and no cross-overlapping; they used the channel trend line method to simul...

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 Patents(China)
IPC IPC(8): G06T17/05
Inventor 胡迅尹艳树冯文杰
Owner YANGTZE UNIVERSITY