Neural control systems trained by dynamic gradient methods for automotive applications
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 798-804
- https://doi.org/10.1109/ijcnn.1992.226889
Abstract
The use of dynamic gradient-based training of neural controllers for automotive systems is illustrated. The authors use a recurrent structure that embeds an identification network and a neural controller and that properly treats both short- and long-term effects of controller weight changes. This results in an approximately optimal control strategy. Feedforward and hybrid feedforward-feedback neural controllers trained by dynamic backpropagation and a dynamic decoupled extended Kalman filter (DDEKF) are investigated. A quarter-car active suspension model is considered in both linear and nonlinear forms, and representative results are presented. Methods using higher-order information, e.g., DDEKF are very effective in comparison to methods based exclusively upon gradient descent, e.g., dynamic backpropagation (DBP). The use of a recurrent structure for obtaining derivatives for controller training is illustrated.Keywords
This publication has 4 references indexed in Scilit:
- Model reference adaptive control with recurrent networks trained by the dynamic DEKF algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Decoupled extended Kalman filter training of feedforward layered networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Gradient methods for the optimization of dynamical systems containing neural networksIEEE Transactions on Neural Networks, 1991
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990