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

Method for predicting liquid holdup of moisture pipeline based on GA-BP neural network

A BP neural network and GA-BP technology, applied in the field of multiphase flow prediction, can solve problems such as poor prediction accuracy and unstable prediction, and achieve the effects of high accuracy, wide application range and fast speed

Pending Publication Date: 2021-12-24
XI'AN PETROLEUM UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional BP neural algorithm has great randomness in the selection of initial weights and thresholds, which is accompanied by problems such as poor prediction accuracy and unstable prediction.

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
  • Method for predicting liquid holdup of moisture pipeline based on GA-BP neural network
  • Method for predicting liquid holdup of moisture pipeline based on GA-BP neural network
  • Method for predicting liquid holdup of moisture pipeline based on GA-BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The following is attached figure 1 The inventive method is described in further detail:

[0034] The method of predicting liquid holdup of wet gas pipeline based on GA-BP neural network, the calculation process is shown in figure 1 , the steps include:

[0035] Step 1: Determine the initial structure of the BP neural network

[0036] Generally, the design of neural network should give priority to 3-layer network (that is, there is 1 hidden layer). Increasing the number of hidden layers can reduce network error and improve accuracy, but it also complicates the network, thereby increasing the training time of the network and "over-fitting". together" tendency.

[0037] The neural network designed and used by the present invention is a 3-layer network.

[0038] A total of 6 influencing variables, such as the pipe diameter, pressure, gas velocity, liquid velocity, temperature, and liquid phase viscosity of the wet gas pipeline, are used as the input of the input layer o...

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 discloses a method for predicting the liquid holdup of a moisture pipeline based on a GA-BP neural network, and the method comprises the steps: collecting and analyzing a large amount of moisture pipeline experiment data, and carrying out the large amount of machine learning as cloud data; constructing a BP neural network optimized by a genetic algorithm, and mainly performing the following work: determining an initial structure of the BP neural network; determining the population size, the coding length and the fitness in the genetic algorithm; selecting a genetic operator; calculating an optimal weight and an optimal threshold; checking the model accuracy; and calculating the liquid holdup parameter of the moisture pipeline system. In order to overcome the defects of the BP neural network, the genetic algorithm is adopted to optimize the BP neural network, the principle of survival of the fittest is followed, good global search performance is achieved, the defect of local optimum of the BP algorithm is well overcome, meanwhile, the initial weight and threshold value of the BP neural network can be optimized, and the calculation precision of the BP neural network is further improved. The application range is wide, and the accuracy rate is up to 95% or above. Besides a moisture pipeline, the method is also suitable for predicting the liquid holdup flow parameter of the gas-liquid two-phase flow in the industrial fields of power engineering, nuclear energy utilization, chemical engineering and the like.

Description

technical field [0001] The invention relates to a gas-liquid flow parameter prediction method based on GA (genetic algorithm)-BP neural network, which is used for online prediction of liquid holdup of wet gas pipelines, and belongs to the field of multiphase flow prediction. Background technique [0002] As one of the main strategic resources in the world today, oil has an unshakable position, and countries have caused wars because of the competition for oil energy. However, in the process of oil and gas field development, oil field output mainly includes oil, natural gas and water, among which oil and water are mixed. In order to reduce production costs, they are usually transported in the form of mixture. In the process of wet gas pipeline transportation, gas-liquid mixed transportation is usually used for transportation, which not only reduces the economic cost of single-phase transportation after gas-liquid separation, but also saves the construction period and improves ...

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 Applications(China)
IPC IPC(8): G06F30/27G06N3/08G06N3/12G06F113/08G06F113/14
CPCG06F30/27G06N3/126G06N3/084G06N3/086G06F2113/14G06F2113/08
Inventor 肖荣鸽靳帅帅王栋庄琦刘博
Owner XI'AN PETROLEUM UNIVERSITY
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