0
Technical Briefs

A Neural Network Based Nonlinear Model of a Servopneumatic System

[+] Author and Article Information
J. Falcão Carneiro

 IDMEC, Faculdade de Engenharia, Universidade do Porto, Rua Dr Roberto Frias s/n, 4200-465 Porto, Portugaljpbrfc@fe.up.pt

F. Gomes de Almeida

 IDMEC, Faculdade de Engenharia, Universidade do Porto, Rua Dr Roberto Frias s/n, 4200-465 Porto, Portugal

J. Dyn. Sys., Meas., Control 134(2), 024502 (Dec 30, 2011) (8 pages) doi:10.1115/1.4005360 History: Received January 21, 2011; Revised September 19, 2011; Published December 30, 2011; Online December 30, 2011

The use of pneumatic devices is widespread among different industrial fields, in tasks like handling or assembly. Pneumatic systems are low-cost, reliable, and compact solutions. However, its use is typically restricted to simple tasks due to the poor performance achieved in applications where accurate motion control is required. One of the key elements required to achieve a good control performance is the model of the servopneumatic system. An accurate model may be of vital importance not only in the simulation steps needed to test the control strategy but also as a part of the controller itself. This work presents a new servopneumatic system model primarily developed for control tasks, namely, to predict pneumatic and friction forces in dynamic tests. The model can also be used in simulation tasks to predict the piston position and velocity. The performance on both applications is validated experimentally.

Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Experimental setup

Grahic Jump Location
Figure 2

Pneumatic servosystem schematic representation

Grahic Jump Location
Figure 3

Schematic representation of a 3 orifices servovalve

Grahic Jump Location
Figure 4

Static characteristic of the servovalve

Grahic Jump Location
Figure 5

Setup used for experimental friction values acquisition

Grahic Jump Location
Figure 6

Experimental friction data

Grahic Jump Location
Figure 7

Surface of the function Fatr  = f (dx/dt, d2 x/dt2 )

Grahic Jump Location
Figure 8

Friction force modeled by FANN: (a) friction surface and (b) training error

Grahic Jump Location
Figure 9

Open loop trials: (a) control action, (b) Fpneu of the model and system

Grahic Jump Location
Figure 10

Experimental validation: servopneumatic system configuration

Grahic Jump Location
Figure 11

Experimental validation for control applications: series-parallel configuration

Grahic Jump Location
Figure 12

Experimental validation for control applications: (a) Fpneu and (b) Fatr results for ω = 2π rad s−1

Grahic Jump Location
Figure 13

Validation test for simulation applications: parallel configuration

Grahic Jump Location
Figure 14

Experimental validation for simulation applications: position prediction

Grahic Jump Location
Figure 15

Experimental validation for simulation applications: velocity prediction

Tables

Errata

Discussions

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 Journal Articles
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