Browse Publications Technical Papers 2002-01-1149
2002-03-04

Neural Network Based Feedforward Control for Electronic Throttles 2002-01-1149

This paper addresses feedforward tracking control for electronic throttles. A robust and accurate tracking control scheme based on the training of a Neural Network model and feedback term (PID) is developed. The Neural Network based term can be trained off-line. This feedfoward term serves as a mathematical model capable of describing Electronic Throttle dynamics over a wide range. We have shown that by adding the Neural Network based feedforward control to a common feedback control method, such as the gain-scheduled PID used in many ETC production controllers, that the tracking control performance criteria such as transient errors, steady state errors, response time and overshoot, are greatly improved. Experiments conducted on a production Electronic Throttle Body with a Motorola H-brigde driver IC have shown good results utilizing this approach.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Members save up to 18% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.
We also recommend:
TECHNICAL PAPER

Measurement of the Wall-Wetting Dynamics of a Sequential Injection Spark Ignition Engine

940447

View Details

TECHNICAL PAPER

Model Identification for the A/F Path of an SI Engine

970612

View Details

TECHNICAL PAPER

A Practical, Simulation Based Approach to the Teaching of Engine Mapping and Calibration Fundamentals

2011-01-1109

View Details

X