Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

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

A neural network and time series technology, applied in flow characteristics, measurement devices, instruments, etc., can solve the problems of low imaging accuracy, difficult measurement of small signals, poor real-time performance, etc., to improve accuracy, fast learning speed, pattern recognition and The effect of strong classification ability

Inactive Publication Date: 2005-09-07
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this technology has shortcomings such as difficulty in measuring small signals, low imaging accuracy, and poor real-time performance, and further research is needed

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific implementation of the present invention will be further described below in conjunction with the real-time online flow pattern identification of oil-gas two-phase flow in horizontal pipes carried out on a large-scale multiphase flow experimental simulation device.

[0026] (1) Fix and change the liquid phase flow and gas phase flow respectively to obtain various flow patterns of different flow conditions, different gas and liquid flows: such as laminar flow, stirred flow, slug flow and annular flow. The differential pressure signal time series of the gas-liquid two-phase flow in the horizontal pipe is collected by a differential pressure sensor. The sampling point spacing is 10 times the pipe diameter, the sampling frequency is 200Hz, and the sampling time is 30 seconds.

[0027] (2) After the wavelet transform method is used to denoise the obtained time series signals, and through data processing, the probability density function curves of differential pres...

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 relates to a method for identifying the flow pattern of the two-phase, which combines the nerval net pattern identifying technology with the traditional time series frequency function statistical method and identifies on line, real time and automatically. The method comprise the following steps: a)processing the flow parameter time series of different flow pattern and getting the characteristic parameters of the frequency function of different flow pattern, b) setting the characteristic parameters as input samples, c) mapping from the measuring space to the flow pattern space by the nerval net identifying technology and identifying the flow pattern.

Description

technical field [0001] The present invention relates to a gas-liquid two-phase flow pattern identification method, in particular to a two-phase flow pattern identification method based on time series and neural network pattern identification, which can carry out online identification of gas-liquid two-phase horizontal pipe flow pattern recognition methods. It belongs to the technical field of multiphase flow measurement and control and data processing. Background technique [0002] Two-phase flow flow pattern identification is the basis of two-phase flow scientific research. The determination of flow pattern provides reliable parameters for the design, operation and operation of two-phase flow systems and related equipment, as well as the calculation of pressure drop along the pipeline. The design, analysis and operation of the system are of great significance. In the past 30 years, many flow pattern recognition methods based on different models and theories have been prop...

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
IPC IPC(8): G01N11/00G01N33/00G09F17/00
Inventor 王经贾志海牛刚
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products