Tracking performance comparison for different strategies in output PDF control

Author

Yue, Hong ; Wang, Hong ; Zhang, Jinfang ; Chai, Tianyou

Author_Institution

Sch. of Electr. & Electron. Eng., Manchester Univ.

fYear

2006

fDate

14-16 June 2006

Abstract

Two predictive PDF control algorithms and one new algorithm of iterative learning PDF control have been compared with the standard PDF control of dynamic systems. The two predictive algorithms are developed on the general 2-norm distance and the Kullback-Leibler performance, respectively. A new iterative algorithm is proposed in which the control input in the current batch is updated based on the control input and the PDF tracking errors in the previous batch. Simulation studies demonstrate the improvement in PDF tracking performance when advanced control strategies are introduced to the standard algorithm

Keywords

iterative methods; learning systems; predictive control; probability; Kullback-Leibler performance; general 2-norm distance; iterative algorithm; iterative learning PDF control; output PDF control; predictive PDF control; probability density function; tracking performance comparison; Algorithm design and analysis; Automatic control; Automation; Control systems; Iterative algorithms; Optimal control; Prediction algorithms; Predictive models; Shape control; Spline;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 2006

Conference_Location

Minneapolis, MN

Print_ISBN

1-4244-0209-3

Electronic_ISBN

1-4244-0209-3

Type

conf

DOI

10.1109/ACC.2006.1655481

Filename

1655481