Application of improved BP neural network in identification of air-water two-phase flow patterns

ZHOU Yunlong; SUN Bin; LU Jun

您当前的位置：

首页 >

文章列表页 >

Application of improved BP neural network in identification of air-water two-phase flow patterns

更新时间：2025-12-10

- Application of improved BP neural network in identification of air-water two-phase flow patterns
- CIESC Journal Issue 1, Pages: 110-115(2005)
- 作者机构：
  
  1. 东北电力学院,吉林,吉林,132012
  2. 华北电力大学,河北,保定,071003
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：25 January 2005，
  
  Published：25 January 2005
- 稿件说明：
移动端阅览
ZHOU Yunlong, SUN Bin, LU Jun. Application of improved BP neural network in identification of air-water two-phase flow patterns[J]. CIESC Journal, 2005, (1): 110-115.
DOI：

ZHOU Yunlong, SUN Bin, LU Jun. Application of improved BP neural network in identification of air-water two-phase flow patterns[J]. CIESC Journal, 2005, (1): 110-115. DOI：

摘要

采用统计理论与分形理论相结合的方法对水平管内空气-水两相流的压差波动信号进行分析，得到了压差均值、标准差、偏斜度、能量份额、盒维数、关联维数和Hurst指数7个参数，并将上述参数作为流型的特征向量输入自适应学习率的改进BP神经网络，通过对训练样本的学习，网络可以实现对未知流型的客观识别.仿真结果表明：统计参数与分形参数相结合得到的流型特征向量可以很好地反映各流型之间的差异，网络识别率高达93%，并且改进后的BP网络具有收敛速度快、不易陷入局部极小的优点.

Abstract

The pressure difference fluctuation signals of the air-water two-phase flow in a horizontal pipe were analyzed by statistical and fractal theory.Seven parameters

i.e. the averaged value of the pressure difference

standard deviation

skewness，energy ratio

box dimension，correlation dimension and Hurst index were obtained and be used as the characteristic vector of an improved BP neural network with self-adapted learning ratio. Learning form training samples

the network could accomplish the objective identification of the unknown flow patterns.The simulated results showed that the flow pattern characteristic vector which was obtained by statistical and fractal parameters could reflect the difference between various flow patterns and the recognition possibility of the network could reached up to about 93 percent.Moreover

the improved BP neural network had the merits of fast convergence for simulation and avoidance of local minimum.

关键词

Keywords

references

Views

213

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Double variable PID decoupling control of headbox based on BP neural network

Identification of gas-liquid two-phase flow pattern based on wavelet energy feature

Improved L-M algorithm for ANNs prediction of phase equilibrium in macromolecule system

Study on microstructure of NaCl solution ice centrifugal separation based on Micro-CT and deep learning

Study on impact of impurities in coal chemical waste salt on solvation of NaCl and Na2SO4

Related Author

PAN Haipeng

XU Yuying

ZHOU Yunlong

WANG Qiang

YANG Zhihang

SUN Bin

CHEN Xiaobo

WANG Liyuan

Related Institution

浙江理工大学自动化研究所

东北电力大学动力系

中国科学院过程工程研究所

郑州大学化工学院

⁰