A fracturing data cleaning method based on genetic algorithm optimized bp neural network

A BP neural network and genetic algorithm technology, which is applied in the field of oil and gas fracturing construction, can solve the problems of slow detection and removal speed, high consumption of manpower, material resources and financial resources

Active Publication Date: 2022-07-12
SOUTHWEST PETROLEUM UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The manual cleaning method is simple to operate, but with the increase of the data scale, it needs a lot of manpower, material resources, and financial resources, and the detection and removal speed will be much slower

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
  • A fracturing data cleaning method based on genetic algorithm optimized bp neural network
  • A fracturing data cleaning method based on genetic algorithm optimized bp neural network
  • A fracturing data cleaning method based on genetic algorithm optimized bp neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] The present invention is described below by taking the fracturing data collected in real time in the period of 587746s-589251s from the fracturing wells in the YY block of XX oilfield as an example.

[0073] (1) During the fracturing operation, some fracturing data are derived from the fracturing instrument car, and the reservoir data is taken as an example to illustrate. . The normal threshold range of fracturing data is determined by geological conditions, such as parameter open flow rate; the open flow range of most medium-production wells that have achieved good fracturing effect in this block is (10-20) × 10 4 m 3 / d (that is, the PJKXD column in the table) (due to different industry standards, here 10 4 is 10000 or 10 to the 4th power);

[0074] Table 1

[0075]

[0076]

[0077]

[0078]

[0079] (2) Manually judge whether these data are in the normal threshold interval for this column of data, and the mark in the normal threshold interval is "A=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 fracturing data cleaning method based on a BP neural network optimized by a genetic algorithm, which includes first manually judging whether a part of the fracturing data is abnormal and marking it, and then taking 75% of the marked data as the genetic algorithm-optimized data. The training sample set of the BP neural network, the remaining 25% of the labeled data is taken as the test sample set of the network; the "dirty data" existing in all fracturing real-time construction data is automatically identified by pattern recognition. The fracturing data cleaning method of the present invention is different from traditional manual cleaning. The method has a high degree of automation and can greatly improve work efficiency and accuracy. By analyzing the fracturing data after cleaning, it can further effectively guide the fracturing site construction and reduce Misjudgment in decision-making, and the purpose of judging the expected effect of fracturing and developing oil and gas fields reasonably and efficiently.

Description

technical field [0001] The invention belongs to the technical field of oil and natural gas fracturing construction, in particular to a fracturing data cleaning method based on a BP neural network optimized by a genetic algorithm. Background technique [0002] Analysis of fracturing operation data is an important means to evaluate the effect of reservoir stimulation and to judge the expected effect of fracturing. In the process of fracturing data acquisition, due to the failure of the acquisition equipment, the human operation does not meet the specifications and other reasons will cause abnormal data and input abnormality, which makes some "dirty data" in the original data. Data cleaning is the process of detecting and eliminating "dirty data" by screening outliers in the data in the database. [0003] Data cleaning in massive data is undoubtedly a complex and arduous task. The existing cleaning solutions are usually those formed according to the data characteristics of dif...

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): G06F16/215G06K9/62G06N3/08G06N3/12
CPCG06N3/08G06N3/084G06N3/126G06F18/2433
Inventor 梁海波王怡杨海李忠兵
Owner SOUTHWEST PETROLEUM UNIV
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