Title :
KDE based output PDF control for nonlinear non-Gaussian systems using PSO algorithm
Author :
Yin Liping ; Zhang Hongyan ; Zhou Li ; Wang Hong
Author_Institution :
Sch. of Inf. & Control, Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Abstract :
This paper considers a simplified PDF control strategy for non-linear non-Gaussian stochastic distribution systems. The objective of this approach is still to make the output probability density function track a desired PDF. The output PDF, which is assumed to be immeasurable, is estimated according to kernel density estimation by analyzing the output sequence of the system. The performance index is constructed with respect to the control objective and is minimized based on particle swarm optimization. A PDF tracking controller is then designed and a simulation is finally given to demonstrate the effectiveness and efficiency of the proposed algorithm.
Keywords :
control system synthesis; nonlinear control systems; particle swarm optimisation; performance index; statistical distributions; stochastic systems; KDE; PDF tracking controller design; PSO algorithm; kernel density estimation; nonlinear nonGaussian stochastic distribution systems; output PDF control; output probability density function; particle swarm optimization; performance index minimisation; Algorithm design and analysis; Kernel; Performance analysis; Probability density function; Process control; Stochastic processes; Stochastic systems; Kernel density estimation(KDE); Non-Gaussian system; Non-linear systems; Particle swarm optimization(PSO); Probability density function(PDF); Stochastic distribution control; Tracking control;
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
DOI :
10.1109/ChiCC.2014.6895852
