Work diagram feature extraction and diagnosis evaluation method based on freeman chain code

A feature extraction and evaluation method technology, applied in data processing applications, instruments, calculations, etc., can solve problems such as low diagnostic accuracy, difficulty in obtaining learning samples, and evaluation of collected power maps, and achieve the effect of easy viewing and fast and accurate judgment

Pending Publication Date: 2022-07-01
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above methods all need to be based on the working condition model library, and it is difficult to obtain enough learning samples in the early stage, resulting in a long period of building the working condition model library, which leads to a low diagnostic accuracy in the early stage, and the traditional working condition analysis method is only a simple Giving a diagnosis result does not make an overall and detailed evaluation of the acquisition work map. The on-site operators can only make judgments based on the results given, lacking a self-learning process

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
  • Work diagram feature extraction and diagnosis evaluation method based on freeman chain code
  • Work diagram feature extraction and diagnosis evaluation method based on freeman chain code
  • Work diagram feature extraction and diagnosis evaluation method based on freeman chain code

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0125] like Figures 13a to 13c , is the normalized pump power diagram after the conversion of the three pumping well dynamometer diagrams to be diagnosed.

[0126] Perform boundary chain code conversion on it, and the result is as follows Figure 14a ~ Figure 14c .

[0127] Extract its 12 feature vectors, the specific values ​​are as follows:

[0128]

[0129] Combined with the judgment rules of the occurrence degree of each feature, typical working conditions and feature pattern sets, the actual working conditions with diagnostic samples are given: each feature vector of sample 1 is not in the judgment rules that may occur, so the working conditions of this sample are normal work; Sample 2, feature 7, feature 10, and feature 11 satisfy the judgment rule z 1 , combined with the typical working condition-feature pattern set, it can be determined that the sample working condition is insufficient liquid supply; the sample 3 feature 5, feature 6, and feature 9 satisfy the j...

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 an indicator diagram feature extraction and diagnosis evaluation method based on freeman chain codes, and the method comprises the steps: analyzing an oil well ground indicator diagram, converting a pump indicator diagram, building a chain code diagram corresponding to the indicator diagram based on the freeman chain codes, carrying out the feature extraction of the chain code diagram, extracting key information in the chain codes, and extracting 12 feature vectors. The method comprises the following steps: extracting feature vectors of oil fields, combining common working conditions of the oil fields with the extracted feature vectors, establishing a typical working condition-feature mode set, giving out judgment rules of each typical working condition through the mode set, establishing a working condition evaluation system, giving out the occurrence degree of each feature of the indicator diagram, and scoring. Rapid diagnosis modeling and accurate analysis of working conditions are achieved, management of oil field personnel is facilitated, and fine management of the pumping well is achieved.

Description

technical field [0001] The invention relates to the field of oil-pumping well production patterns, in particular to a method for extracting and diagnosing power map features based on freeman chain codes. Background technique [0002] With the deepening of oilfield exploitation, the increase in the number of oil wells, and the emergence of complex situations such as high viscosity, sand, water flooding and strong corrosion, the probability of accidents in the rod pumping system is increasing. Therefore, the development of rod pump Well fault diagnosis and evaluation system is of great significance. By monitoring the data and parameters fed back by the oil pumping system, the system realizes real-time analysis of the data and judges and diagnoses the cause of the system fault, and takes timely measures for the oil wells that find the accident, thereby reducing the economic loss caused by the accident. [0003] At present, some achievements have been made in the research on th...

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 & AuthorityApplications(China)
IPC IPC(8): G06K9/62G06Q10/06
CPCG06Q10/06393G06F18/214
Inventor郑东梁曾鹏李世超石硕张立婷凌霄
OwnerSHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI