Rod-pumped well pump inspection period prediction method based on support vector regression algorithm

A technology of support vector regression and pump inspection cycle, applied in construction and other directions, can solve problems such as increased operating costs, economic losses, production losses, etc., to achieve the effect of strengthening connection and improving accuracy

Pending Publication Date: 2021-04-16
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Frequent pump inspections not only cause production loss, but also increase operating costs, and due to reasons such as the service life and the number of operating teams, sometimes some oil wells have a long waiting time for operation, which seriously affects oil well production and causes huge economic losses.

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
  • Rod-pumped well pump inspection period prediction method based on support vector regression algorithm
  • Rod-pumped well pump inspection period prediction method based on support vector regression algorithm
  • Rod-pumped well pump inspection period prediction method based on support vector regression algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to illustrate the technical solution of the present invention more clearly, the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0021] The flow chart of a method for predicting pumping well inspection period based on support vector regression algorithm described in this embodiment is as follows figure 1 , the method is specifically implemented through the following steps:

[0022] 1. Collected 10 consecutive years of pumping unit status data in the oil field, generated data, and pump inspection cycle data. Specifically, such as daily oil production, daily water production, daily gas production, daily production time, water content, upward current, downward current, stroke times, stroke, pump diameter, pump depth, displacement, maximum load, minimum load, etc. are obtained as the algorithm. The independent variable is required, and the period of each pump inspection of the pumping well in the ...

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 designs a rod-pumped well pump inspection period prediction method based on a support vector regression (SVR) algorithm, and belongs to the technical field of oil well detection. The method includes the steps of acquiring a related pump inspection period data set; performing data cleaning and data preprocessing; finding out main control factors through a gray correlation analysis algorithm; constructing a data volume based on a sliding window method; and establishing models according to the SVR algorithm, and finding an optimal precision model for prediction. Due to the adoption of the technical scheme, the serious influence and huge economic loss on well oil production caused by the limitation of the service life of an oil well pump, the number of operation teams and the like can be better solved, and a new pump inspection period prediction mode is provided for an oil field pump inspection method.

Description

technical field [0001] The invention relates to a period prediction method, in particular to a support vector regression (SVR) algorithm-based method for predicting the period of a pump well inspection pump, and belongs to the technical field of oil well inspection. Background technique [0002] In the mechanical oil recovery process, the rod pump oil recovery method occupies a very important position in my country's crude oil recovery. At present, oilfields widely adopt maintenance strategies for pumping wells, that is, maintenance is carried out when some faults cause the oil wells to fail to produce normally. Frequent pump inspections not only cause production loss, but also increase operating costs. Due to the limitation of service life and the number of operating teams, some oil wells sometimes have a long waiting time for operation, which seriously affects the production of oil wells and causes huge economic losses. [0003] In recent years, the method of condition-ba...

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): E21B47/009
Inventor 刘新平邓杰杨鹏磊张晓东
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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