ELECTRICA

An Analysis of the Effects of SVM Parameters on the Dead-Time System Modeling

1.

Department of Electrical and Electronics Engineering, İstanbul Medeniyet University School of Engineering and Natural Science, İstanbul, Turkey

2.

Department of Electrical and Electronics Engineering, İstanbul University School of Engineering, İstanbul, Turkey

ELECTRICA 2018; 18: 1-5
DOI: 10.5152/iujeee.2018.1801
Read: 1016 Downloads: 604 Published: 23 February 2018

Modeling a dead-timesystem is a common issue in engineering applications. To address this issue,existing research has employed neural networks and fuzzy logic-based intelligentsystems. Herein, a dead-time system modeled with the aid of support vectormachine regression, which has a good generalization feature, was investigated.The performance of the method proposed herein was examined with differentparameters in linear and nonlinear dead-time systems.

Files
EISSN 2619-9831