Unlock instant, AI-driven research and patent intelligence for your innovation.

A simulation method of pumping unit running trajectory based on high-resolution representation learning

A high-resolution, trajectory technology, applied in the field of petroleum engineering, to achieve spatially accurate results

Active Publication Date: 2022-07-19
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the measurement of stroke times and suspension point displacement of traditional pumping units requires the use of professional instruments, this invention proposes a method for simulating the operation trajectory of pumping units based on high-resolution characterization learning. With the help of multi-resolution parallel networks, the key Spot heat map prediction, saving oilfield costs

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 simulation method of pumping unit running trajectory based on high-resolution representation learning
  • A simulation method of pumping unit running trajectory based on high-resolution representation learning
  • A simulation method of pumping unit running trajectory based on high-resolution representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0120] In order to prove the feasibility of the present invention, the following experiments were carried out.

[0121] The proposed technology is tested by taking the image taken by the actual pumping unit of an oil field and the sample data collected by the web crawler as an example, and the subsequent analysis and discussion are carried out. Then follow the steps below to simulate the running trajectory of the oilfield pumping unit.

[0122] Step 1. Build a parallel multi-resolution network model. In terms of network level settings, the convolution layer and the pooling layer are selected twice, and then enter the four-level multi-resolution parallel network layer, and the network finally outputs the experimental results only through the high-resolution backbone network.

[0123] Step 2. Set model parameters. Randomly initialize network parameters, convolution parameter weights w and bias b , feature fusion layer parameters The default value is 0, the initial learning...

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 a method for simulating the running trajectory of a pumping unit based on high-resolution representation learning, belonging to the technical field of petroleum engineering, and comprising the steps of: constructing a parallel multi-resolution network model; setting model parameters; collecting image data of the pumping unit Set, label key points and make sample sets; enhance data set; input parallel multi-resolution network model for multi-resolution parallel convolution; multi-resolution fusion; output heat map of predicted key point locations; error back propagation, optimize the learner parameters; output the heat map for prediction of key points of the pumping unit; model evaluation; online application of the output model. The high-resolution representation of the key points of the pumping unit learned by the method of the present invention is not only strong in semantics, but also accurate in space. By means of the multi-resolution parallel network, the invention realizes the prediction of the heat map of the key points, simulates the running track of the pumping unit, and saves the cost of the oil field.

Description

technical field [0001] The invention belongs to the technical field of petroleum engineering, in particular to a method for simulating the running trajectory of a pumping unit based on high-resolution representation learning. Background technique [0002] Oil is called "black gold" and has become an important strategic material in the world today. As large as the national industry, agriculture, national defense, and as small as everyone's food, clothing, housing and transportation, they are all inseparable from oil. Therefore, it is of great practical significance to continuously improve the technical level of oilfield development. The petrochemical industry can only develop continuously only by continuously carrying out related research work, strengthening the training of professional and technical personnel, enabling them to master and adopt advanced scientific research achievements, strengthening technological innovation of independent intellectual property rights, and c...

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): G06F30/27G06N3/04G06N3/08G06V10/80
CPCG06F30/27G06N3/084G06N3/045G06F18/253
Inventor 张凯王强赵捍军张庆杰罗有刚张华清张黎明严侠刘丕养杨勇飞孙海姚军樊灵
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)