Identification of a Hydraulic Servo-Axis Using Support Vector Machines
| Authors: | Schaab Jochen, University of Technology at Darmstadt, Germany
Muenchhof Marco, University of Technology at Darmstadt, Germany
Vogt Michael, University of Technology at Darmstadt, Germany
Isermann Rolf, University of Technology at Darmstadt, Germany |
|---|
| Topic: | 1.1 Modelling, Identification & Signal Processing |
|---|
| Session: | Nonlinear System Identification - Kernel Methods |
|---|
| Keywords: | hydraulic actuators, system identification, support vector machines, neuralnetworks, nonlinear modelling |
|---|
Abstract
In this paper, different models of the pressure buildup inside a hydraulic servoaxisare compared. These models are derived using RBF networks, local linear modelsand support vector machines (SVMs), with a particular focus on the latter. For SVMs,a reduction method is derived, which allows to reduce the number of support vectorswithout losing the generalization abilities of the SVM. Experimental results obtained ata hydraulic servo-axis and a comparison of the different modelling techniques concludethis paper.
