Combining support vector machines with linear quadratic regulator adaptation for the online design of an automotive active suspension system

As a powerful machine-learning approach to pattern recognition problems, the support vector machine (SVM) is known to easily allow generalization. More importantly, it works very well in a high-dimensional feature space. This paper presents a nonlinear active suspension controller which achieves a h...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2008-02, Vol.96 (1), p.012095
Main Authors: Chiou, J-S, Liu, M-T
Format: Article
Language:English
Subjects:
Actuators
Controllers
Feedback control
Linear quadratic regulator
Machine learning
Nonlinear control
Nonlinear systems
Optimal control
Pattern recognition
Physics
State feedback
Support vector machines
Suspension systems
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a powerful machine-learning approach to pattern recognition problems, the support vector machine (SVM) is known to easily allow generalization. More importantly, it works very well in a high-dimensional feature space. This paper presents a nonlinear active suspension controller which achieves a high level performance by compensating for actuator dynamics. We use a linear quadratic regulator (LQR) to ensure optimal control of nonlinear systems. An LQR is used to solve the problem of state feedback and an SVM is used to address the question of the estimation and examination of the state. These two are then combined and designed in a way that outputs feedback control. The real-time simulation demonstrates that an active suspension using the combined SVM-LQR controller provides passengers with a much more comfortable ride and better road handling.
ISSN:1742-6596
1742-6588
1742-6596
DOI:10.1088/1742-6596/96/1/012095