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

Oil well working condition intelligent diagnosis analysis method and device based on SVM model

A technology of intelligent diagnosis and analysis methods, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as limited application scope, inability to provide high-accuracy power map identification methods, complex and changeable oil well conditions, etc. To achieve the effect of accurate identification

Pending Publication Date: 2020-05-12
PETROCHINA CO LTD
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides an intelligent diagnosis and analysis method and device for oil well working conditions based on SVM model. The purpose is to solve the above problems and solve the complex and changeable working conditions of oil wells caused by different oil reservoirs, different well structures and differences in physical properties. The above technologies have limitations in the scope of application. , unable to provide a general high-accuracy power map recognition 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
  • Oil well working condition intelligent diagnosis analysis method and device based on SVM model
  • Oil well working condition intelligent diagnosis analysis method and device based on SVM model
  • Oil well working condition intelligent diagnosis analysis method and device based on SVM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Please refer to figure 1 , which shows a flow chart of an embodiment of the method for intelligent diagnosis and analysis of oil well conditions based on the SVM model provided by an embodiment of the present invention. The method for intelligent diagnosis and analysis of oil well conditions based on the SVM model includes:

[0054] Step 1: Obtain multiple sets of normal dynamometer diagrams of the oil well, and extract the HOG features of the multiple groups of normal dynamometer diagrams, and set the HOG features of the normal dynamometer diagrams into a normal HOG feature set;

[0055] Step 2: Obtain multiple groups of fault dynamometer diagrams of oil wells under different working conditions, divide the multiple groups of dynamometer diagrams into multiple groups of fault sample sets according to different accidents of oil wells, and extract the HOG features of each fault sample set respectively. The HOG feature set of each group of failure sample sets is the accide...

Embodiment 2

[0062] Further, please refer to figure 1 , another embodiment of the present invention based on the SVM model oil well operating condition intelligent diagnosis and analysis method, before the step 4 also includes,

[0063] Step 3.1: Take the normal HOG feature set in normal production as the third sample, take the accident HOG feature set of all accidents as the fourth sample, input the third sample and the fourth sample into the SVM classifier for learning and training, and obtain Normal production diagnostic model for normal production of oil wells;

[0064] In said step 4, after extracting the HOG feature of the oil well indicator diagram to be diagnosed, first use the normal production diagnosis model to diagnose, if the normal production diagnosis model diagnoses the normal production of the oil well, then output the normal result of the oil well, if the normal production diagnosis model diagnoses For oil well failures, extract the HOG features from the oil well dynamom...

Embodiment 3

[0068] Further, please refer to figure 1 , Another embodiment of the present invention is based on the SVM model oil well operating condition intelligent diagnosis and analysis method. The normal production diagnosis model diagnoses the oil well dynamometer diagram that needs to be diagnosed after extracting the HOG feature, specifically:

[0069] The normal production diagnosis model extracts historical normal work diagrams and calculates HOG features. When the normal production diagnosis model diagnoses that the oil well indicator diagrams that need to be diagnosed have a similarity with the historical normal work diagrams greater than 96%, the oil well output is normal.

[0070] In the above-mentioned embodiment, when the normal production diagnosis model diagnoses that the similarity between the oil well indicator map that needs to be diagnosed and the historical normal work map is greater than 96%, it is a preferred embodiment, and it can accurately determine whether there...

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 oil well working condition intelligent diagnosis and analysis method and device based on an SVM model. The invention belongs to the technical field of oil field oil extraction processes, and provides an SVM model-based oil well working condition intelligent diagnosis and analysis method, which comprises the steps of 1, obtaining multiple groups of normal indicator diagrams of an oil well, extracting HOG features of the multiple groups of normal indicator diagrams, and gathering the HOG features of the normal indicator diagrams into a normal HOG feature set; under thecondition that the working conditions of the oil well are complicated and changeable caused by different oil reservoirs and different well bore structures and physical property differences, a set ofuniversal high-accuracy indicator diagram identification method is provided; the problem that matrix features of a matrix feature recognition method do not describe subtle changes of an indicator diagram sufficiently is solved, slight sand production, upward collision and downward hanging can be recognized accurately, the problem that features useful for diagnosis are removed in the actual application process of a differential curve method is solved, the number of diagnosis types is large, and quantitative evaluation can be achieved. Compared with a PSO-RBF neural network algorithm, the methodis more accurate in recognition under complex working conditions.

Description

technical field [0001] The invention belongs to the technical field of oil recovery technology in oil fields, and in particular relates to a method and device for intelligent diagnosis and analysis of oil well working conditions based on an SVM model. Background technique [0002] With the development of digital oilfields, oil well work map telemetry technology is widely used. Diagnosing oil well working conditions (deep well pump working status) through oil well telemetry work map has become one of the important means of daily production management of oil wells. [0003] In recent years, with the development of computer technology, the research on automatic analysis of working conditions with the help of computer systems has been deepened. The current popular technologies include: power diagram moment feature recognition method (oil pumping unit power diagram moment feature recognition method oil and gas field surface engineering ( OGSE) Volume 18, No. 3), differential curv...

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): G06K9/62
CPCG06F18/2411G06F18/214
Inventor 王绍平高占武李永平李科华李广辉刘继红刘彬唐梅向东奎张建东张云龙赵凯峰眭金扩
Owner PETROCHINA CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com