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

Gradient lifting method well cementation quality evaluation method

A quality evaluation and method cementing technology, which is applied in the directions of measurement, earthwork drilling and production, borehole/well components, etc., and can solve the problems of poor timeliness and reliability

Pending Publication Date: 2021-08-20
CHINA NAT OFFSHORE OIL CORP +2
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problems of poor timeliness and reliability of cementing quality evaluation in the prior art, and provide a method for evaluating cementing quality by gradient lifting 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
  • Gradient lifting method well cementation quality evaluation method
  • Gradient lifting method well cementation quality evaluation method
  • Gradient lifting method well cementation quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] like Figure 1 to Figure 4 As shown, a gradient lifting method cementing quality evaluation method specifically includes the following steps:

[0060] S1 Establishing a sample set: selecting a sample well, performing discrete data sampling on the cementing quality evaluation results of the sample well to obtain a sample set;

[0061] S2 establishes a training set and a verification set: perform discretization matching on the sample set established in step S1 with conventional logging values ​​at the same depth point, and randomly separate a certain proportion of the sample set data from the matched sample set data as the training set. The sample set data below is the validation set;

[0062] S3 establishes the primary model of cementing quality evaluation by gradient lifting method: conventional logging values ​​are used as input data, cementing quality evaluation results are used as output data, and loss function and class probability function are used as algorithm co...

Embodiment 2

[0102] This embodiment is similar to Embodiment 1, except that, in this embodiment, the target value of the coincidence rate is 99%, and the coincidence rate of the verification set is 90%. Other parts and working principles of this embodiment are the same as those of Embodiment 1.

Embodiment 3

[0104] This embodiment is similar to Embodiment 1, except that, in this embodiment, the target value of the coincidence rate is 99%, and the coincidence rate of the verification set is 99%. Other parts and working principles of this embodiment are the same as those of Embodiment 1.

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 provides a gradient lifting method well cementation quality evaluation method which comprises the following steps: S1, establishing a sample set; S2, establishing a training set and a verification set; S3, establishing a gradient lifting method well cementation quality evaluation primary model, and standardizing an access end and an output end; S4, optimizing a model: importing the training set data in the step S2 into the gradient lifting method well cementation quality evaluation primary model in the step S3 to be trained and iteratively optimized, so the negative gradient of the model is gradually converged till the coincidence rate of a training result is larger than a coincidence rate target value, parameters are fixed in the model, and an optimized model is obtained; S5, importing verification set data into the optimization model in the step S4, verifying the model, and obtaining a gradient lifting method well cementation quality evaluation model; and S6, applying the model. According to the method, the problems of poor timeliness and reliability of well cementation quality evaluation are solved, model training is carried out through a gradient lifting algorithm, a well logging curve characteristic and well cementation result relation model is established, and rapid and reliable evaluation of well site well cementation quality well logging is achieved.

Description

technical field [0001] The invention relates to the technical field of well logging evaluation of cementing quality in the petroleum industry, and more specifically, relates to a method for evaluating cementing quality by a gradient lifting method. Background technique [0002] Cementing operation means that after the oil well is drilled and the casing is run, the gap between the casing and the formation is filled with cement, so as to realize the tight bonding of the casing, cement and formation. The cementing quality of a well directly affects oil testing and production. When the cementing is not good, the adjacent oil and water layers cannot be completely separated, and the purpose of layered production cannot be achieved, especially when the oil layer and the water layer are connected, which will directly cause the well to be unusable and scrapped. Therefore, timely and effective evaluation of cementing quality is particularly important. Existing methods usually use ac...

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): G06Q10/06G06K9/62E21B47/00
CPCG06Q10/06395G06F18/2415G06F18/214
Inventor 金云智高永德杜超夏如君刘平李伟王继鹏韩玉林曾小明曾楠诺陈小泉车坚女鲁小琴
Owner CHINA NAT OFFSHORE OIL CORP
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