A method and system for calculating the dynamic fluid level of a pumping well by fusing multiple models, an electronic device and a storage medium

By employing a multi-model fusion approach, combining mechanistic analysis, AdaBoost algorithm, and MLP&RNN algorithm with multiple linear regression, the adaptability and accuracy issues of obtaining dynamic fluid level parameters in pumping wells were resolved, achieving more accurate dynamic fluid level prediction and supporting the optimization of well fluid supply capacity and operating procedures.

CN122365425APending Publication Date: 2026-07-10PETROCHINA CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
PETROCHINA CO LTD
Filing Date
2025-01-09
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

In existing technologies, the acquisition of dynamic fluid level parameters in pumping wells suffers from poor adaptability and large errors, affecting the accuracy of judging the fluid supply capacity of oil wells and planning operating procedures.

Method used

A method for back-calculating the dynamic fluid level of pumping wells is constructed by combining mechanistic analysis, AdaBoost algorithm, and MLP&RNN algorithm with multiple linear regression. Data is obtained through oilfield data lake and IoT database, and the data is cleaned and normalized. The dynamic fluid level depth is predicted by combining multiple algorithms.

Benefits of technology

It improves the accuracy and adaptability of dynamic liquid level parameters, provides more accurate data, and supports dynamic analysis and operational system planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122365425A_ABST
    Figure CN122365425A_ABST
Patent Text Reader

Abstract

The application provides a kind of multi-model fusion inverse calculation pumping unit well dynamic liquid level method, system, electronic equipment and storage medium, the method comprises: based on oilfield data lake and oil and gas production internet of things database, obtains dynamic liquid level inverse calculation parameter data and is stored in dynamic liquid level inverse calculation system standard library;With the data in the dynamic liquid level inverse calculation system standard library, respectively through mechanism analysis method model, AdaBoost algorithm and MLP&RNN algorithm, inverse calculation obtains dynamic liquid level depth H1, H2 and H3;Adopt multivariate linear regression method, combine the three inverse calculation results, construct dynamic liquid level fusion refined calculation model, to realize the accurate prediction of actual dynamic liquid level depth H.The application can accurately obtain the dynamic liquid level of pumping unit well, improve the accuracy and adaptability of dynamic liquid level parameter, provide accurate data basis for dynamic analysis to take measures and determine reasonable working system.
Need to check novelty before this filing date? Find Prior Art