Neural network approaches to tracer identification as related to PIV research

PDF Version Also Available for Download.

Description

Neural networks have become very powerful tools in many fields of interest. This thesis examines the application of neural networks to another rapidly growing field flow visualization. Flow visualization research is used to experimentally determine how fluids behave and to verify computational results obtained analytically. A form of flow visualization, particle image velocimetry (PIV). determines the flow movement by tracking neutrally buoyant particles suspended in the fluid. PIV research has begun to improve rapidly with the advent of digital imagers, which can quickly digitize an image into arrays of grey levels. These grey level arrays are analyzed to determine the ... continued below

Physical Description

Pages: (101 p)

Creation Information

Seeley, C.H. Jr. December 1, 1992.

Context

This report is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. More information about this report can be viewed below.

Who

People and organizations associated with either the creation of this report or its content.

Sponsor

Publisher

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this report. Follow the links below to find similar items on the Digital Library.

Description

Neural networks have become very powerful tools in many fields of interest. This thesis examines the application of neural networks to another rapidly growing field flow visualization. Flow visualization research is used to experimentally determine how fluids behave and to verify computational results obtained analytically. A form of flow visualization, particle image velocimetry (PIV). determines the flow movement by tracking neutrally buoyant particles suspended in the fluid. PIV research has begun to improve rapidly with the advent of digital imagers, which can quickly digitize an image into arrays of grey levels. These grey level arrays are analyzed to determine the location of the tracer particles. Once the particles positions have been determined across multiple image frames, it is possible to track their movements, and hence, the flow of the fluid. This thesis explores the potential of several different neural networks to identify the positions of the tracer particles. Among these networks are Backpropagation, Kohonen (counter-propagation), and Cellular. Each of these algorithms were employed in their basic form, and training and testing were performed on a synthetic grey level array. Modifications were then made to them in attempts to improve the results.

Physical Description

Pages: (101 p)

Notes

OSTI; NTIS; INIS; GPO Dep.

Source

  • Other Information: Thesis (M.S.)

Language

Item Type

Identifier

Unique identifying numbers for this report in the Digital Library or other systems.

  • Other: DE93011399
  • Report No.: DOE/ER/12813-T1
  • Grant Number: FG02-88ER12813
  • DOI: 10.2172/6477700 | External Link
  • Office of Scientific & Technical Information Report Number: 6477700
  • Archival Resource Key: ark:/67531/metadc1205837

Collections

This report is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this report?

When

Dates and time periods associated with this report.

Creation Date

  • December 1, 1992

Added to The UNT Digital Library

  • July 5, 2018, 11:11 p.m.

Description Last Updated

  • Aug. 7, 2018, 4 p.m.

Usage Statistics

When was this report last used?

Yesterday: 0
Past 30 days: 1
Total Uses: 1

Interact With This Report

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Seeley, C.H. Jr. Neural network approaches to tracer identification as related to PIV research, report, December 1, 1992; United States. (digital.library.unt.edu/ark:/67531/metadc1205837/: accessed January 20, 2019), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.