Implementing method of sliding directional drilling simulator

A realization method, a technology of directional drilling, which is applied in directional drilling, earthwork drilling, wellbore/well components, etc., and can solve problems such as high cost, large error, and long installation period

Pending Publication Date: 2020-10-20
BC P INC CHINA NAT PETROLEUM CORP +1
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the calculation method using the traditional mathematical model is low in cost, it has the problems of large error, narrow scope of application, and many restrictive conditions. As the exploration and development continue to move towards deep formations, the downhole situation is becoming more and more complex, and it is difficult for the conventional mathematical model to fully consider Various complex conditions downhole, so most of the models are immature, unable to accurately obtain sliding drilling directional data
Using MWD, logging system and other instruments to obtain sliding drilling directional data, compared with the traditional mathematical model, the data accuracy and effectiveness are greatly improved, but there are problems such as high cost, long installation period, frequent fault replacement, and poor data quality. Undoubtedly increased the cost of sliding drilling, while affecting the validity of the data

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
  • Implementing method of sliding directional drilling simulator
  • Implementing method of sliding directional drilling simulator
  • Implementing method of sliding directional drilling simulator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A kind of sliding directional drilling simulator realization method based on GAN that the present invention relates to, such as figure 1 shown, including the following steps:

[0036] (1) Obtain the sliding orientation training data set, and generate random noise at the same time;

[0037] (2) Carry out data processing and data sorting, and generate a model to generate data samples using random noise;

[0038] (3) Use the discriminant model to judge the data source, generate an confrontation network (GAN), and form a sliding directional data model;

[0039] (4) Automatically generate multi-category sliding orientation data, obtain effective amplified data, and form an amplified sliding data set.

[0040] In step (1), the acquired sliding orientation training data set contains at least the data of three systems including torsion pendulum, MWD and mud logging system.

[0041] In step (1), the random noise is equivalent to a random variable, as the input data of the gen...

Embodiment 2

[0053] This embodiment combines the attached figure 2 The calculation flow of the GAN of the present invention will be described.

[0054] Such as figure 2 Shown:

[0055] In the first step, any differentiable function can be used to represent the generative model and discriminant model of GAN. The differentiable functions D and G are used to represent the discriminant model and the generative model respectively. The input of D is the real data x and G(z), The input of G is a random variable z. Among them, G(z) is a data sample generated by G that obeys the real data distribution as much as possible.

[0056] In the second step, if the input of the discriminant model comes from real data, it is marked as 1, and if the input sample is G(z), it is marked as 0.

[0057] In the third step, the goal of D is to realize the two-category discrimination of the data source, and judge whether the data is true (the distribution of real data x) or false (the false data G(z) of the ge...

Embodiment 3

[0060] The sliding orientation training data set is regarded as composed of multiple data points. When processing the sliding orientation training data set, the n×m dimensional "data block" divided by the processed effective data set can be compared to the pixels of the picture Point matrix, each data in the data block is a data step. Then, through the training of the network model combining the convolutional neural network and the generative confrontation network, the purpose of expanding the sequence data sample set can be achieved. Its overall model is as image 3 shown.

[0061] The generative model network structure of the generative confrontation network is as follows: Figure 4 shown. A high-dimensional random noise vector is input into the generation model G, and spatial upsampling is performed through three layers of micro-step convolution layers. The number of channels of the input data is halved, the size of the "data block" is doubled, and finally a 64×64×3 of ...

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 an implementing method of a sliding directional drilling simulator. The implementing method comprises the following steps that a sliding directional training data set is obtained, and meanwhile, random noise is generated; data processing and data arrangement are carried out, and meanwhile, a generation model generates data samples through the random noise; data sources arejudged through a discrimination model, and a generative adversarial network (GAN) forms a sliding directional data model is formed; and multiple categories of sliding directional data are automatically generated, and effective amplification data are obtained to form an amplified sliding data set. According to the implementing method, effective and real data are provided for the discrimination model by providing the sliding directional training data set and carrying out data processing and data arrangement, the data samples are generated through the generation model, and the generated data areprovided for the discrimination model. The discrimination model judges the data sources, the GAN forms the sliding directional data model, the multiple categories of sliding directional data are generated through the sliding directional data model, and thus the purpose of simulating sliding directional parameters through the adversarial network is realized.

Description

technical field [0001] The invention relates to a method for realizing a sliding directional drilling simulator, which is used for acquiring directional data of sliding drilling, and belongs to the field of oil and gas drilling data processing. Background technique [0002] At present, the acquisition of sliding drilling directional data is still dominated by traditional mathematical model calculation and instrument acquisition. Although the calculation method using the traditional mathematical model is low in cost, it has the problems of large error, narrow scope of application, and many restrictive conditions. As the exploration and development continue to move towards deep formations, the downhole situation is becoming more and more complex, and it is difficult for the conventional mathematical model to fully consider Due to various complex conditions downhole, most of the models are immature and cannot accurately obtain the directional data of sliding drilling. Using MW...

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): E21B49/00G06F30/20E21B7/04
CPCE21B49/003G06F30/20E21B7/04Y02T90/00
Inventor 刘伟连太炜陆灯云谭东张德军胡超陈东汪洋谢意冯思恒廖冲
Owner BC P INC CHINA NAT PETROLEUM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap