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

A multi-model prediction method for water content of oil well oil based on time series

A technology of time series and forecasting methods, applied in forecasting, character and pattern recognition, instruments, etc., can solve the problems of time-consuming and labor-intensive manual sampling, affecting production monitoring, etc.

Inactive Publication Date: 2019-11-26
BOHAI UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a time-series-based multi-model forecasting method for water content of oil well oil that solves the time-consuming and labor-intensive manual sampling of water content of oil well oil and affects the real-time performance of production monitoring and oil production data. For some historical periods, the water cut data of oil well oil can be used to predict the water cut data of the next time point

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 multi-model prediction method for water content of oil well oil based on time series
  • A multi-model prediction method for water content of oil well oil based on time series
  • A multi-model prediction method for water content of oil well oil based on time series

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0092] The time-series-based multi-model prediction method of oil well oil water content, the specific steps are as follows:

[0093] 1. Use historical data to establish a data set of water content of oil well oil, including 440 data, expressed as {x i ,i=1,2,…,440}, 440 data are arranged in the order of time points (unit is day), and according to the sequence of data in the oil well oil water content data set, record each data in the oil well oil water content data set The sequence number is {index i ,i=1,2,...,440}.

[0094] 2. Use the wavelet analysis method to analyze the oil well oil water content data set {x i} to preprocess the data, specifically: firstly, {x i} is subjected to three-layer wavelet decomposition, according to the formula (1) to the data set {x i} for decomposition:

[0095]

[0096] Among them, i=1,2,...,440; J=0,1,2; H and G are decomposed low-pass filter and decomposed high-pass filter respectively;

[0097] Then reconstruct according to for...

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 present invention relates to the multi-model prediction method of water content of oil well oil based on time series, is characterized in that, comprises the following steps: 1), utilizes historical data to establish the data set of water content of oil well oil as {x i ,i=1,2,…,N}; 2), using wavelet analysis method to analyze the oil well oil water content data set {x i ,i=1,2,...,N} data in the preprocessing; 3), by the nearest neighbor propagation clustering algorithm {x i} Wave Classify; 4), express the data in each cluster by the following time series form: 5), establish a time series model of each cluster according to the extreme learning machine algorithm, and use the time series model to obtain the predicted value. It solves the problems of time-consuming and labor-intensive manual sampling of the water content of oil in existing oil wells, and affects the real-time performance of production monitoring and oil recovery data.

Description

technical field [0001] The invention relates to the field of petroleum production, in particular to a multi-model prediction method for water content of oil well oil based on time series. Background technique [0002] The water content of oil well oil is an important indicator of oil field production, not only related to the development life of oil well, but also related to the economic benefits of enterprises. Therefore, it is of great significance to measure the oil well production accurately, evaluate the production value and production degree of the oil reservoir, and formulate the production plan. At present, the method of manual sampling and re-distillation is still widely used to measure the water content of oil well oil. The workers regularly go to the oil well for manual sampling, and then send the oil back to the technical department for experimental analysis. This method is time-consuming and laborious, and affects production monitoring and control. The real-time...

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): G06F17/50G06K9/62
CPCG06Q10/04G06Q50/02G06F18/24147
Inventor 李琨韩莹魏泽飞佘东生杨一柳于震
Owner BOHAI UNIV
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