Intelligent identification method of two-phase flow pattern based on principal component analysis and support vector machine

Through the combination of principal component analysis and support vector machine, the problem of gas-liquid two-phase flow type recognition in porous media is solved, and fast and accurate flow type recognition is achieved, which reduces the calculation amount and improves the recognition accuracy. It is suitable for gas-liquid two-phase flow type detection in porous media.

CN116340823BActive Publication Date: 2025-08-12XI AN JIAOTONG UNIV
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202310306889.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-03-27
Publication Date
2025-08-12
Estimated Expiration
2043-03-27

AI Technical Summary

Technical Problem

The prior art is difficult to quickly and accurately identify the two-phase flow patterns of gas-liquid flow in porous media, and research has been mainly focused on conventional pipelines and cannot be effectively applied to porous media structures.

Method used

The method of combining principal component analysis and support vector machine is adopted to construct coupled feature vectors through pressure differential signal acquisition, time domain and frequency domain analysis, and feature extraction, and flow type recognition is used by support vector machines to achieve intelligent gas-liquid two-phase flow flow type recognition in porous media.

Benefits of technology

It realizes rapid and accurate identification of two-phase gas-liquid flow patterns in porous media, reduces the calculation amount, improves the recognition accuracy, and provides technical support for actual industrial production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116340823B_ABST
    Figure CN116340823B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for intelligently identifying two-phase flow patterns based on principal component analysis and support vector machines. The method utilizes a differential pressure transmitter and a data acquisition system to collect the original gas-liquid two-phase differential pressure signal within a porous medium channel online. The method utilizes the probability density function in time domain analysis and the power spectral density technique in frequency domain analysis to statistically extract the time and frequency domain characteristic parameters of the two-phase differential pressure signal, respectively. The method integrates physical parameters such as the Reynolds number of the gas and liquid two-phase flows to construct a coupled characteristic vector that comprehensively reflects the two-phase flow pattern. Furthermore, the method utilizes principal component analysis and support vector machine techniques to propose and establish an intelligent system and method for identifying two-phase flow patterns within porous media, achieving rapid identification of gas-liquid two-phase flow patterns within porous media. The principal component analysis-support vector machine fusion method proposed in the present invention is highly accurate and interpretable, and is of great significance for improving the identification technology for gas-liquid two-phase flow patterns in porous media and for identifying gas-liquid two-phase flow patterns.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • PCA mixed feature fusion based gas-liquid two-phase flow type identification method

    CN105426889A

  • System for quickly recognizing gathering-transportation riser system gas-liquid two-phase flow mass flow pattern

    CN105823617A

  • Two-phase fluid flow pattern identification method based on time sequence and neural net pattern identification

    CN1664555A

  • Dense medium suspension liquid coal slurry content determination method by using principal component analysis and support vector machine

    CN101608994A

  • Online identification method for gas-liquid two-phase-flow flow pattern in gathering and transportation-vertical pipe system

    CN104807589A