Intelligent Identification of Flow Regime Based on Improved BP and IMFs

Qiang Wang

doi:10.4028/www.scientific.net/AMR.816-817.471

Paper Titles

The Analysis of Rogowski Coil Transfer Characteristics in the Composite Frequency Environment
p.450

Study on the Straight-Line Running Stability of Off-Road Vehicle with In-Wheel Motors
p.454

Surface Modification of Polypropylene Blood Oxygenator Membrane by Poly Ethylene Glycol Grafting
p.459

Control Method for Improving Efficiency of Digital Inkjet Printing
p.467

Intelligent Identification of Flow Regime Based on Improved BP and IMFs
p.471

Design and Implementation of Web-Based Archive Dispatching Management System
p.475

A Trusted Model in the Internet of Water Transport
p.479

Performance Analysis of the Wiener Optimal Filtering Noise-Reduction Technique
p.484

Applications of Distributed Parallel Real Time Database on Power Grid
p.488

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 816-817Intelligent Identification of Flow Regime Based on...

Intelligent Identification of Flow Regime Based on Improved BP and IMFs

Abstract:

Aimed at the characteristic of nonlinear and non-stationary of pressure drop, in this article a flow regime identification soft sensing method using Hilbert-Huang transformation combined with improved BP neural network is put forward. The method analyzes the intrinsic mode function (IMFs) obtained after the empirical mode decomposition (EMD), then extracts IMF energy 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 regimes. The simulated results showed that the flow regime characteristic vector which was obtained by IMFs could reflect the difference between various flow regimes and the recognition possibility of the network could reached up to about 95 percent. This study provided a new way to identify flow regime by soft sensing.

You might also be interested in these eBooks

Manufacturing Science and Technology (ICMST2013)

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 816-817)

Pages:

471-474

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.816-817.471

Citation:

Cite this paper

Online since:

September 2013

Authors:

Qiang Wang

Keywords:

Flow Regime Identification, Improved BP Neural Network, Intrinsic Mode Functions

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] S Z Rouhani. Two-phase flow patters：a review of research results [J]．Nucl．Energy，1983，11(3), pp.219-259.

Google Scholar

[2] Y Mi, M Ishii, L H Tsoukalas. Flow regime identification methodology with neural networks and two-phase flow models [J]. Nuclear Engineering and Design，2001，204(1-3), pp.87-100.

DOI: 10.1016/s0029-5493(00)00325-3

Google Scholar

[3] Y Mi , M Ishii. Vertical Two-Phase Flow Recognition Using Advanced Instrumentation and Neural Networks[J]. Nuclear Engineering and Design, 1998, 184, pp.409-420.

DOI: 10.1016/s0029-5493(98)00212-x

Google Scholar

[4] Y LI, MQ Chen. Operation Performance Diagnosis Technology and Its Application for Steam Turbine [M]. Science Press, Beijing, 1999, PP. 91-120.

Google Scholar

[5] Q Wang, YL Zhou , YF Cui, et al. Applied study of EMD and neural networks on flow regime identification for gas-liquid two-phase flow [J]. Journal of Engineering Thermophysics, 2007, 28(3), PP. 442-4.

Google Scholar