0
Research Papers

A Neural Network Implementation of Peak Pressure Position Control by Ionization Current Feedback

[+] Author and Article Information
N. Rivara, P. B. Dickinson

Department of Engineering, University of Liverpool, Liverpool L69 3GH, UK

A. T. Shenton

Department of Engineering, University of Liverpool, Liverpool L69 3GH, UKshenton@liv.ac.uk

Integrated over 180 deg prior to sampling.

J. Dyn. Sys., Meas., Control 131(5), 051003 (Aug 17, 2009) (8 pages) doi:10.1115/1.3155009 History: Received January 08, 2008; Revised April 01, 2009; Published August 17, 2009

This paper describes a neural-network (NN)-based scheme for the control of a cylinder peak pressure position (PPP)—also known as the location of peak pressure (LPP)—by spark timing in a gasoline internal combustion engine. The scheme uses the ionization current to act as a virtual sensor, which is subsequently used for PPP control. A NN is trained offline on principal-component analysis data to predict the cylinder peak pressure position under dynamically varying engine load, speed, and spark advance (SA) settings. Experimental results demonstrate that the PPP prediction by the NN correlates well with those measured from in-cylinder pressure sensors across transients of load, SA, and engine speeds. The dynamic training data allow rapid model identification across the identified engine range, as opposed to just fixed operating points. A linear robust constrained-variance controller, which is a robustified form of the minimum variance controller, is used to regulate the PPP by SA control action, using the NN as a PPP sensor. The control scheme is validated by experimental implementation on a port fuel-injected four-cylinder 1.6 l gasoline internal combustion engine.

Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Actual cylinder pressure and a typical ionization current signal from a nonaveraged combustion cycle

Grahic Jump Location
Figure 2

Identification system

Grahic Jump Location
Figure 3

Schematic of a two layer NARX network

Grahic Jump Location
Figure 4

3000 cycles of engine speed (N), integrated MAP, and PPP identification data

Grahic Jump Location
Figure 5

3000 cycles of five PCA scores’ identification data

Grahic Jump Location
Figure 6

Predicted and actual PPPs

Grahic Jump Location
Figure 7

Correlation of normalized and scaled predicted PPPs and normalized and scaled actual PPPs over 1000 cycles

Grahic Jump Location
Figure 8

Correlation of predicted and actual PPPs over 1000 cycles due to step changes in ABV

Grahic Jump Location
Figure 9

Correlation of predicted and actual PPPs over 1000 cycles due to step changes in SA

Grahic Jump Location
Figure 10

Correlation of predicted and actual PPPs over 1000 cycles due to step changes in applied load

Grahic Jump Location
Figure 11

Implemented closed-loop feedback control

Grahic Jump Location
Figure 12

Loci of possible controller gains for σy2=1.1 deg2

Grahic Jump Location
Figure 13

Step response of four controllers

Grahic Jump Location
Figure 14

Predicted PPP and actual PPP tracking to demanded PPP and required spark advance

Grahic Jump Location
Figure 15

Predicted PPP and actual PPP tracking to demanded PPP with step disturbances to ABV

Grahic Jump Location
Figure 16

Predicted PPP and actual PPP tracking to demanded PPP with step disturbances to load

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