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

Robust lithology identification method

A technology of lithology identification and lithology, applied in earthwork drilling, wellbore/well components, measurement, etc., can solve problems such as poor robustness, lithology identification, failure to reflect the value of key samples, etc., and achieve high operating efficiency , the effect of strong robustness

Pending Publication Date: 2022-08-02
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]However, these lithology identification methods based on machine learning did not propose a specific model for lithology identification, but only applied the existing general model
There are some problems in the practical application of this method. For example, the output weight of the model weights all training samples and does not reflect the value of key samples, so its robustness is often poor.

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
  • Robust lithology identification method
  • Robust lithology identification method
  • Robust lithology identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] This part will describe the specific embodiments of the present invention in detail, and the preferred embodiments of the present invention are shown in the accompanying drawings. Each technical feature and overall technical solution of the invention should not be construed as limiting the protection scope of the invention.

[0029] refer to figure 1 As shown, it is a flow chart of a robust lithology identification method according to an embodiment of the present invention, and the method includes the following steps:

[0030] Step 1. Construct a set of labeled samples of the existing logging data, and obtain the existing logging data. All logging values ​​at each depth form a feature vector, that is, a sample, and the logging values ​​include natural gamma and natural potential. , well diameter, acoustic transit time, density, compensated neutrons, deep lateral resistivity, and shallow lateral resistivity; a sample is expressed as x∈R d×1 , where R represents the rea...

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 robust lithology prediction method, which comprises the following steps: 1) constructing a labeled sample set of existing logging data; 2) initializing a system; 3) generating a kernel matrix; 4) calculating an optimal output weight matrix; compared with the prior art, the method has the following advantages that 1) model parameters are analytic, so that the method has extremely high operation efficiency, and 2) sparsity constraints are introduced to force output weights to weaken the weights of secondary samples and highlight main samples, so that the method has relatively high robustness.

Description

technical field [0001] The invention relates to the fields of structural geology and petroleum geology, in particular to a robust lithology identification method. Background technique [0002] Lithology identification has always been a key analysis problem in geological engineering research. In the prior art, lithology identification mainly includes geological research method, intersection diagram method and lithology identification using mathematical algorithm. Predictions may not be consistent. [0003] Machine learning methods emerging in recent years have injected fresh blood into lithology identification. For example, a method for lithology identification is disclosed in the prior art. The method firstly determines the target logging data file, performs format conversion and normalization preprocessing, and then according to With known lithology, perform feature screening and / or feature combination expansion on logging curve data to obtain logging curve data sensitiv...

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): E21B49/00E21B47/00
CPCE21B49/00E21B47/00
Inventor 韩宏伟冯德永刘海宁隋志强罗荣涛刘鸽姜蕾江洁
Owner CHINA PETROLEUM & CHEM CORP