0

Full Content is available to subscribers

Subscribe/Learn More  >

Pressure Measurement and Pattern Recognition by Using Neural Networks

[+] Author Affiliations
Parham Piroozan

Indiana Institute of Technology

Paper No. IMECE2005-79745, pp. 897-905; 9 pages
doi:10.1115/IMECE2005-79745
From:
  • ASME 2005 International Mechanical Engineering Congress and Exposition
  • Dynamic Systems and Control, Parts A and B
  • Orlando, Florida, USA, November 5 – 11, 2005
  • Conference Sponsors: Dynamic Systems and Control Division
  • ISBN: 0-7918-4216-9 | eISBN: 0-7918-3769-6
  • Copyright © 2005 by ASME

abstract

This paper describes an intelligent control system that uses electro-optics and neural networks to control the flow of air over a flexible wall. In this investigation a pressure sensor which was part of the wall of the wind tunnel and an optical apparatus were used to produce moiré fringes. A back propagation neural network was used to analyze the fringe patterns and to classify the pressures into four levels. A second neural network was used to recognize the pressure patterns and to provide the input to a control system that was capable of modifying the shape of the flexible wall in order to preserve the stability of the flow. The flexible wall was part of the wall of the wind tunnel and was installed in the upstream of the flow. It was made of silicone rubber and had an area of 76 mm by 76 mm. There were 15 rows of actuators installed under the flexible wall which were used to change the shape of the wall. In the downstream of the flow was an optical pressure sensor which had the same dimensions as the flexible wall and consisted of a 15 × 15 array of small diaphragms. These diaphragms responded to the pressure fluctuations in the boundary layer flow and were the source of the signals for the optical system. A CCD camera viewed the pressure sensor through an optical apparatus which produced moiré fringes. A back propagation neural network analyzed the fringe patterns and classified the pressures into four levels. The classified pressures which was a 15 × 15 array of numbers ranging from 1 to 4 was the input to a second back propagation neural network which was used to recognize the pressure patterns. The output from the back propagation neural network used for pattern recognition provided the input to a control system that changed the shape of the flexible wall. This paper presents the experimental results as well as the computer simulations which were created for this project. This includes the complete process of creating the slope fringes, classifying the pressures into four levels, recognizing the wall pressure patterns and generating the output signals to the actuator for changing the shape of the flexible wall.

Copyright © 2005 by ASME

Figures

Tables

Interactive Graphics

Video

Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

NOTE:
Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In